The KITTI Vision Benchmark Suite

The bird's eye view benchmark consists of 7481 training images and 7518 test images as well as the corresponding point clouds, comprising a total of 80.256 labeled objects. For evaluation, we compute precision-recall curves. To rank the methods we compute average precision. We require that all methods use the same parameter set for all test pairs. Our development kit provides details about the data format as well as MATLAB / C++ utility functions for reading and writing the label files.

• Download left color images of object data set (12 GB)
• Download right color images, if you want to use stereo information (12 GB)
• Download the 3 temporally preceding frames (left color) (36 GB)
• Download the 3 temporally preceding frames (right color) (36 GB)
• Download Velodyne point clouds, if you want to use laser information (29 GB)
• Download camera calibration matrices of object data set (16 MB)
• Download training labels of object data set (5 MB)
• Download object development kit (1 MB) (including 3D object detection and bird's eye view evaluation code)
• Download pre-trained LSVM baseline models (5 MB) used in Joint 3D Estimation of Objects and Scene Layout (NIPS 2011). These models are referred to as LSVM-MDPM-sv (supervised version) and LSVM-MDPM-us (unsupervised version) in the tables below.
• Download reference detections (L-SVM) for training and test set (800 MB)
• Qianli Liao (NYU) has put together code to convert from KITTI to PASCAL VOC file format (documentation included, requires Emacs).
• Karl Rosaen (U.Mich) has released code to convert between KITTI, KITTI tracking, Pascal VOC, Udacity, CrowdAI and AUTTI formats.
• We thank David Stutz and Bo Li for developing the 3D object detection benchmark.

We evaluate bird's eye view detection performance using the PASCAL criteria also used for 2D object detection. Far objects are thus filtered based on their bounding box height in the image plane. As only objects also appearing on the image plane are labeled, objects in don't car areas do not count as false positives. We note that the evaluation does not take care of ignoring detections that are not visible on the image plane — these detections might give rise to false positives. For cars we require a bounding box overlap of 70% in bird's eye view, while for pedestrians and cyclists we require an overlap of 50%. Difficulties are defined as follows:

• Easy: Min. bounding box height: 40 Px, Max. occlusion level: Fully visible, Max. truncation: 15 %
• Moderate: Min. bounding box height: 25 Px, Max. occlusion level: Partly occluded, Max. truncation: 30 %
• Hard: Min. bounding box height: 25 Px, Max. occlusion level: Difficult to see, Max. truncation: 50 %

All methods are ranked based on the moderately difficult results.

Car

	Method	Setting	Code	Moderate	Easy	Hard	Runtime	Environment
1	VirConv-S		code	93.52 %	95.99 %	90.38 %	0.09 s	1 core @ 2.5 Ghz (C/C++)
H. Wu, C. Wen, S. Shi and C. Wang: Virtual Sparse Convolution for Multimodal 3D Object Detection. CVPR 2023.
2	UDeerPEP		code	93.40 %	95.34 %	89.07 %	0.1 s	1 core @ 2.5 Ghz (C/C++)
Z. Dong, H. Ji, X. Huang, W. Zhang, X. Zhan and J. Chen: PeP: a Point enhanced Painting method for unified point cloud tasks. 2023.
3	VirConv-T		code	92.65 %	96.11 %	89.69 %	0.09 s	1 core @ 2.5 Ghz (C/C++)
H. Wu, C. Wen, S. Shi and C. Wang: Virtual Sparse Convolution for Multimodal 3D Object Detection. CVPR 2023.
4	GraR-Po		code	92.12 %	95.79 %	87.11 %	0.06 s	1 core @ 2.5 Ghz (Python + C/C++)
H. Yang, Z. Liu, X. Wu, W. Wang, W. Qian, X. He and D. Cai: Graph R-CNN: Towards Accurate 3D Object Detection with Semantic-Decorated Local Graph. ECCV 2022.
5	TSSTDet			92.11 %	95.80 %	89.23 %	0.08 s	1 core @ 2.5 Ghz (C/C++)
H. Hoang, D. Bui and M. Yoo: TSSTDet: Transformation-Based 3-D Object Detection via a Spatial Shape Transformer. IEEE Sensors Journal 2024.
6	MPCF			92.07 %	95.92 %	87.29 %	0.08 s	1 core @ 2.5 Ghz (C/C++)
7	TED		code	92.05 %	95.44 %	87.30 %	0.1 s	1 core @ 2.5 Ghz (C/C++)
H. Wu, C. Wen, W. Li, R. Yang and C. Wang: Transformation-Equivariant 3D Object Detection for Autonomous Driving. AAAI 2023.
8	MB3D			91.93 %	95.33 %	88.71 %	0.09 s	1 core @ 2.5 Ghz (C/C++)
9	PVFusion		code	91.87 %	95.01 %	86.96 %	0.01 s	1 core @ 2.5 Ghz (C/C++)
10	VPFNet		code	91.86 %	93.02 %	86.94 %	0.06 s	2 cores @ 2.5 Ghz (Python)
H. Zhu, J. Deng, Y. Zhang, J. Ji, Q. Mao, H. Li and Y. Zhang: VPFNet: Improving 3D Object Detection with Virtual Point based LiDAR and Stereo Data Fusion. IEEE Transactions on Multimedia 2022.
11	SFD		code	91.85 %	95.64 %	86.83 %	0.1 s	1 core @ 2.5 Ghz (Python + C/C++)
X. Wu, L. Peng, H. Yang, L. Xie, C. Huang, C. Deng, H. Liu and D. Cai: Sparse Fuse Dense: Towards High Quality 3D Detection with Depth Completion. CVPR 2022.
12	SE-SSD		code	91.84 %	95.68 %	86.72 %	0.03 s	1 core @ 2.5 Ghz (Python + C/C++)
W. Zheng, W. Tang, L. Jiang and C. Fu: SE-SSD: Self-Ensembling Single-Stage Object Detector From Point Cloud. CVPR 2021.
13	HDet3D			91.82 %	94.90 %	84.68 %	0.07 s	>8 cores @ 2.5 Ghz (Python)
14	LVP(84.92)			91.80 %	95.49 %	88.91 %	0.04 s	1 core @ 2.5 Ghz (C/C++)
15	ACFNet			91.78 %	92.91 %	87.06 %	0.11 s	1 core @ 2.5 Ghz (C/C++)
Y. Tian, X. Zhang, X. Wang, J. Xu, J. Wang, R. Ai, W. Gu and W. Ding: ACF-Net: Asymmetric Cascade Fusion for 3D Detection With LiDAR Point Clouds and Images. IEEE Transactions on Intelligent Vehicles 2023.
16	GraR-Vo		code	91.72 %	95.27 %	86.51 %	0.04 s	1 core @ 2.5 Ghz (C/C++)
H. Yang, Z. Liu, X. Wu, W. Wang, W. Qian, X. He and D. Cai: Graph R-CNN: Towards Accurate 3D Object Detection with Semantic-Decorated Local Graph. ECCV 2022.
17	NIV-SSD			91.69 %	95.66 %	86.72 %	0.03 s	1 core @ 2.5 Ghz (C/C++)
18	CDF			91.67 %	92.68 %	86.62 %	0.08 s	1 core @ 2.5 Ghz (C/C++)
19	PVT-SSD			91.63 %	95.23 %	86.43 %	0.05 s	1 core @ 2.5 Ghz (Python + C/C++)
H. Yang, W. Wang, M. Chen, B. Lin, T. He, H. Chen, X. He and W. Ouyang: PVT-SSD: Single-Stage 3D Object Detector with Point-Voxel Transformer. CVPR 2023.
20	HAF-PVP_test			91.60 %	95.33 %	86.71 %	0.09 s	1 core @ 2.5 Ghz (C/C++)
21	SPANet			91.59 %	95.59 %	86.53 %	0.06 s	1 core @ 2.5 Ghz (C/C++)
Y. Ye: SPANet: Spatial and Part-Aware Aggregation Network for 3D Object Detection. Pacific Rim International Conference on Artificial Intelligence 2021.
22	CasA		code	91.54 %	95.19 %	86.82 %	0.1 s	1 core @ 2.5 Ghz (C/C++)
H. Wu, J. Deng, C. Wen, X. Li and C. Wang: CasA: A Cascade Attention Network for 3D Object Detection from LiDAR point clouds. IEEE Transactions on Geoscience and Remote Sensing 2022.
23	FEIF3D			91.53 %	95.29 %	86.87 %	0.1 s	GPU @ 2.5 Ghz (Python)
24	LoGoNet		code	91.52 %	95.48 %	87.09 %	0.1 s	1 core @ 2.5 Ghz (C/C++)
X. Li, T. Ma, Y. Hou, B. Shi, Y. Yang, Y. Liu, X. Wu, Q. Chen, Y. Li, Y. Qiao and others: LoGoNet: Towards Accurate 3D Object Detection with Local-to-Global Cross-Modal Fusion. CVPR 2023.
25	GraR-Pi		code	91.52 %	95.06 %	86.42 %	0.03 s	1 core @ 2.5 Ghz (C/C++)
H. Yang, Z. Liu, X. Wu, W. Wang, W. Qian, X. He and D. Cai: Graph R-CNN: Towards Accurate 3D Object Detection with Semantic-Decorated Local Graph. ECCV 2022.
26	MM-UniMODE			91.51 %	95.69 %	88.71 %	0.04 s	1 core @ 2.5 Ghz (Python)
27	MAK_VOXEL_RCNN			91.46 %	95.32 %	86.81 %	0.03 s	1 core @ 2.5 Ghz (Python)
28	UPIDet		code	91.36 %	92.96 %	86.80 %	0.11 s	1 core @ 2.5 Ghz (C/C++)
Y. Zhang, Q. Zhang, J. Hou, Y. Yuan and G. Xing: Unleash the Potential of Image Branch for Cross-modal 3D Object Detection. Thirty-seventh Conference on Neural Information Processing Systems 2023.
29	BADet		code	91.32 %	95.23 %	86.48 %	0.14 s	1 core @ 2.5 Ghz (C/C++)
R. Qian, X. Lai and X. Li: BADet: Boundary-Aware 3D Object Detection from Point Clouds. Pattern Recognition 2022.
30	Anonymous			91.30 %	95.26 %	86.73 %	0.1 s	1 core @ 2.5 Ghz (Python)
31	ANM		code	91.30 %	94.91 %	88.51 %	ANM	ANM
32	DEF-Model			91.28 %	93.03 %	86.48 %	0.03 s	1 core @ 2.5 Ghz (C/C++)
33	SSLFusion			91.26 %	94.86 %	88.55 %	0.5 s	1 core @ 2.5 Ghz (C/C++)
34	TED-S Reproduced			91.23 %	95.34 %	86.68 %	0.1 s	1 core @ 2.5 Ghz (Python)
ERROR: Wrong syntax in BIBTEX file.
35	URFormer			91.22 %	94.40 %	86.35 %	0.1 s	1 core @ 2.5 Ghz (Python)
36	CasA++		code	91.22 %	94.57 %	88.43 %	0.1 s	1 core @ 2.5 Ghz (C/C++)
H. Wu, J. Deng, C. Wen, X. Li and C. Wang: CasA: A Cascade Attention Network for 3D Object Detection from LiDAR point clouds. IEEE Transactions on Geoscience and Remote Sensing 2022.
37	OGMMDet		code	91.21 %	95.59 %	88.33 %	0.01 s	1 core @ 2.5 Ghz (C/C++)
38	voxel_spark		code	91.18 %	94.82 %	86.58 %	0.04 s	GPU @ 2.5 Ghz (C/C++)
39	spark			91.13 %	94.93 %	86.54 %	0.1 s	1 core @ 2.5 Ghz (Python)
40	3D HANet		code	91.13 %	94.33 %	86.33 %	0.1 s	1 core @ 2.5 Ghz (C/C++)
Q. Xia, Y. Chen, G. Cai, G. Chen, D. Xie, J. Su and Z. Wang: 3D HANet: A Flexible 3D Heatmap Auxiliary Network for Object Detection. IEEE Transactions on Geoscience and Remote Sensing 2023.
41	test			91.12 %	93.93 %	86.17 %	0.1 s	1 core @ 2.5 Ghz (C/C++)
42	DiffCandiDet			91.11 %	95.05 %	86.45 %	0.06 s	GPU @ 2.5 Ghz (Python + C/C++)
43	spark_voxel_rcnn		code	91.08 %	94.61 %	86.59 %	0.04 s	1 core @ 2.5 Ghz (Python)
44	voxel-rcnn+++		code	91.06 %	92.84 %	86.27 %	0.08 s	GPU @ 2.5 Ghz (Python)
45	SA-SSD		code	91.03 %	95.03 %	85.96 %	0.04 s	1 core @ 2.5 Ghz (Python)
C. He, H. Zeng, J. Huang, X. Hua and L. Zhang: Structure Aware Single-stage 3D Object Detection from Point Cloud. CVPR 2020.
46	L-AUG			91.00 %	94.52 %	88.08 %	0.1 s	1 core @ 2.5 Ghz (C/C++)
T. Cortinhal, I. Gouigah and E. Aksoy: Semantics-aware LiDAR-Only Pseudo Point Cloud Generation for 3D Object Detection. 2023.
47	TED_S_baseline		code	90.98 %	94.56 %	86.41 %	0.09 s	1 core @ 2.5 Ghz (Python)
48	spark2			90.95 %	92.93 %	86.44 %	0.1 s	1 core @ 2.5 Ghz (C/C++)
49	HS-fusion			90.95 %	93.77 %	87.79 %	- s	1 core @ 2.5 Ghz (Python)
ERROR: Wrong syntax in BIBTEX file.
50	Voxel_Spark_focal_we		code	90.93 %	94.83 %	86.45 %	0.08 s	1 core @ 2.5 Ghz (Python)
51	c2f			90.89 %	92.31 %	86.25 %	1 s	1 core @ 2.5 Ghz (C/C++)
52	3D Dual-Fusion		code	90.86 %	93.08 %	86.44 %	0.1 s	1 core @ 2.5 Ghz (Python)
Y. Kim, K. Park, M. Kim, D. Kum and J. Choi: 3D Dual-Fusion: Dual-Domain Dual-Query Camera-LiDAR Fusion for 3D Object Detection. arXiv preprint arXiv:2211.13529 2022.
53	PR-SSD			90.78 %	94.23 %	86.14 %	0.02 s	GPU @ 2.5 Ghz (Python)
54	MLFusion-VS			90.78 %	95.10 %	88.41 %	0.06 s	1 core @ 2.5 Ghz (C/C++)
55	GraphAlign(ICCV2023)		code	90.73 %	94.46 %	88.34 %	0.03 s	GPU @ 2.0 Ghz (Python)
Z. Song, H. Wei, L. Bai, L. Yang and C. Jia: GraphAlign: Enhancing accurate feature alignment by graph matching for multi-modal 3D object detection. Proceedings of the IEEE/CVF International Conference on Computer Vision 2023.
56	GF-pointnet			90.67 %	93.88 %	86.09 %	0.02 s	1 core @ 2.5 Ghz (C/C++)
57	SDGUFusion			90.65 %	95.10 %	86.45 %	0.5 s	1 core @ 2.5 Ghz (C/C++)
58	MMLab PV-RCNN		code	90.65 %	94.98 %	86.14 %	0.08 s	1 core @ 2.5 Ghz (Python + C/C++)
S. Shi, C. Guo, L. Jiang, Z. Wang, J. Shi, X. Wang and H. Li: PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detection. CVPR 2020.
59	SQD			90.63 %	95.44 %	88.04 %	0.06 s	1 core @ 2.5 Ghz (C/C++)
60	focalnet			90.61 %	94.46 %	88.12 %	0.05 s	1 core @ 2.5 Ghz (C/C++)
61	BPG3D			90.57 %	93.00 %	86.21 %	0.05 s	1 core @ 2.5 Ghz (Python)
62	focalnet			90.56 %	94.52 %	88.08 %	0.05 s	1 core @ 2.5 Ghz (C/C++)
63	VPFNet		code	90.52 %	93.94 %	86.25 %	0.2 s	1 core @ 2.5 Ghz (C/C++)
C. Wang, H. Chen and L. Fu: VPFNet: Voxel-Pixel Fusion Network for Multi-class 3D Object Detection. 2021. C. Wang, H. Chen, Y. Chen, P. Hsiao and L. Fu: VoPiFNet: Voxel-Pixel Fusion Network for Multi-Class 3D Object Detection. IEEE Transactions on Intelligent Transportation Systems 2024.
64	ECA			90.50 %	93.87 %	85.94 %	0.08 s	GPU @ 1.5 Ghz (Python)
65	PDV		code	90.48 %	94.56 %	86.23 %	0.1 s	1 core @ 2.5 Ghz (C/C++)
J. Hu, T. Kuai and S. Waslander: Point Density-Aware Voxels for LiDAR 3D Object Detection. CVPR 2022.
66	LGNet-3classes		code	90.44 %	94.98 %	86.06 %	0.11 s	1 core @ 2.5 Ghz (C/C++)
67	Spark_PartA2_Soft_fo		code	90.38 %	93.90 %	85.91 %	0.1 s	1 core @ 2.5 Ghz (Python)
68	M3DeTR		code	90.37 %	94.41 %	85.98 %	n/a s	GPU @ 1.0 Ghz (Python)
T. Guan, J. Wang, S. Lan, R. Chandra, Z. Wu, L. Davis and D. Manocha: M3DeTR: Multi-representation, Multi- scale, Mutual-relation 3D Object Detection with Transformers. 2021.
69	VoTr-TSD		code	90.34 %	94.03 %	86.14 %	0.07 s	1 core @ 2.5 Ghz (C/C++)
J. Mao, Y. Xue, M. Niu, H. Bai, J. Feng, X. Liang, H. Xu and C. Xu: Voxel Transformer for 3D Object Detection. ICCV 2021.
70	HA-PillarNet			90.33 %	94.29 %	85.99 %	0.05 s	1 core @ 2.5 Ghz (Python)
71	MSIT-Det			90.24 %	96.01 %	80.53 %	0.06 s	1 core @ 2.5 Ghz (Python + C/C++)
72	Spark_partA22			90.23 %	92.61 %	85.89 %	10 s	1 core @ 2.5 Ghz (Python)
73	DSA-PV-RCNN		code	90.13 %	92.42 %	85.93 %	0.08 s	1 core @ 2.5 Ghz (Python + C/C++)
P. Bhattacharyya, C. Huang and K. Czarnecki: SA-Det3D: Self-Attention Based Context-Aware 3D Object Detection. 2021.
74	LFT			90.12 %	95.83 %	85.06 %	0.1s	1 core @ 2.5 Ghz (C/C++)
75	XView			90.12 %	92.27 %	85.94 %	0.1 s	1 core @ 2.5 Ghz (C/C++)
L. Xie, G. Xu, D. Cai and X. He: X-view: Non-egocentric Multi-View 3D Object Detector. 2021.
76	SFA-GCL		code	90.12 %	95.75 %	84.97 %	0.04 s	1 core @ 2.5 Ghz (C/C++)
77	SFA-GCL(80)		code	90.11 %	95.76 %	84.96 %	0.04 s	1 core @ 2.5 Ghz (C/C++)
78	GraR-VoI		code	90.10 %	95.69 %	86.85 %	0.07 s	1 core @ 2.5 Ghz (Python + C/C++)
H. Yang, Z. Liu, X. Wu, W. Wang, W. Qian, X. He and D. Cai: Graph R-CNN: Towards Accurate 3D Object Detection with Semantic-Decorated Local Graph. ECCV 2022.
79	CAT-Det			90.07 %	92.59 %	85.82 %	0.3 s	GPU @ 2.5 Ghz (Python + C/C++)
Y. Zhang, J. Chen and D. Huang: CAT-Det: Contrastively Augmented Transformer for Multi-modal 3D Object Detection. CVPR 2022.
80	3ONet			90.07 %	95.87 %	85.09 %	0.1 s	1 core @ 2.5 Ghz (C/C++)
H. Hoang and M. Yoo: 3ONet: 3-D Detector for Occluded Object Under Obstructed Conditions. IEEE Sensors Journal 2023.
81	SFA-GCL(80, k=4)		code	90.04 %	95.67 %	84.91 %	0.04 s	1 core @ 2.5 Ghz (C/C++)
82	focal			90.02 %	94.56 %	85.95 %	100 s	1 core @ 2.5 Ghz (Python)
83	GeVo			90.02 %	92.45 %	85.86 %	0.05 s	1 core @ 2.5 Ghz (C/C++)
84	spark-part2			90.01 %	93.82 %	85.89 %	0.1 s	1 core @ 2.5 Ghz (C/C++)
ERROR: Wrong syntax in BIBTEX file.
85	SP_SECOND_IOU		code	89.95 %	92.23 %	85.84 %	0.04 s	1 core @ 2.5 Ghz (Python)
86	CG-SSD			89.93 %	94.26 %	85.76 %	0.01 s	1 core @ 2.5 Ghz (C/C++)
87	Anonymous		code	89.91 %	93.38 %	84.91 %	0.04 s	1 core @ 2.5 Ghz (Python)
88	OFFNet			89.88 %	91.62 %	85.57 %	0.1 s	GPU @ 2.5 Ghz (Python)
89	SVGA-Net			89.88 %	92.07 %	85.59 %	0.03s	1 core @ 2.5 Ghz (Python + C/C++)
Q. He, Z. Wang, H. Zeng, Y. Zeng and Y. Liu: SVGA-Net: Sparse Voxel-Graph Attention Network for 3D Object Detection from Point Clouds. AAAI 2022.
90	EBM3DOD		code	89.86 %	95.64 %	84.56 %	0.12 s	1 core @ 2.5 Ghz (Python)
F. Gustafsson, M. Danelljan and T. Schön: Accurate 3D Object Detection using Energy- Based Models. arXiv preprint arXiv:2012.04634 2020.
91	U_PV_V2_ep_100_100			89.86 %	92.17 %	85.81 %	0.1 s	1 core @ 2.5 Ghz (C/C++)
92	CIA-SSD		code	89.84 %	93.74 %	82.39 %	0.03 s	1 core @ 2.5 Ghz (Python + C/C++)
W. Zheng, W. Tang, S. Chen, L. Jiang and C. Fu: CIA-SSD: Confident IoU-Aware Single-Stage Object Detector From Point Cloud. AAAI 2021.
93	MLF-DET			89.82 %	93.38 %	84.78 %	0.09 s	1 core @ 2.5 Ghz (C/C++)
Z. Lin, Y. Shen, S. Zhou, S. Chen and N. Zheng: MLF-DET: Multi-Level Fusion for Cross- Modal 3D Object Detection. International Conference on Artificial Neural Networks 2023.
94	CLOCs_PVCas		code	89.80 %	93.05 %	86.57 %	0.1 s	1 core @ 2.5 Ghz (Python)
S. Pang, D. Morris and H. Radha: CLOCs: Camera-LiDAR Object Candidates Fusion for 3D Object Detection . 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) 2020.
95	VoxelFSD			89.79 %	92.57 %	85.77 %	0.08 s	1 core @ 2.5 Ghz (Python)
96	GLENet-VR		code	89.76 %	93.48 %	84.89 %	0.04 s	1 core @ 2.5 Ghz (C/C++)
Y. Zhang, Q. Zhang, Z. Zhu, J. Hou and Y. Yuan: GLENet: Boosting 3D object detectors with generative label uncertainty estimation. International Journal of Computer Vision 2023. Y. Zhang, J. Hou and Y. Yuan: A Comprehensive Study of the Robustness for LiDAR-based 3D Object Detectors against Adversarial Attacks. International Journal of Computer Vision 2023.
97	RDIoU		code	89.75 %	94.90 %	84.67 %	0.03 s	1 core @ 2.5 Ghz (Python + C/C++)
H. Sheng, S. Cai, N. Zhao, B. Deng, J. Huang, X. Hua, M. Zhao and G. Lee: Rethinking IoU-based Optimization for Single- stage 3D Object Detection. ECCV 2022.
98	PV-RCNN-Plus			89.75 %	91.93 %	85.77 %	1 s	1 core @ 2.5 Ghz (C/C++)
99	SFA-GCL(baseline)		code	89.74 %	95.55 %	84.63 %	0.04 s	1 core @ 2.5 Ghz (C/C++)
100	SFA-GCL_dataaug		code	89.73 %	93.44 %	84.60 %	0.04 s	1 core @ 2.5 Ghz (C/C++)
101	SFA-GCL		code	89.71 %	93.53 %	84.58 %	0.04 s	1 core @ 2.5 Ghz (C/C++)
102	DGEnhCL		code	89.66 %	95.21 %	84.53 %	0.04 s	1 core @ 2.5 Ghz (C/C++)
103	EBM3DOD baseline		code	89.63 %	95.44 %	84.34 %	0.05 s	1 core @ 2.5 Ghz (Python)
F. Gustafsson, M. Danelljan and T. Schön: Accurate 3D Object Detection using Energy- Based Models. arXiv preprint arXiv:2012.04634 2020.
104	SCNet3D			89.61 %	93.36 %	84.78 %	0.08 s	1 core @ 2.5 Ghz (Python)
105	VPA			89.61 %	95.46 %	86.81 %	0.01 s	1 core @ 2.5 Ghz (C/C++)
ERROR: Wrong syntax in BIBTEX file.
106	MAK		code	89.59 %	93.21 %	86.84 %	0.03 s	GPU @ 2.5 Ghz (Python)
107	pointpillars_spark		code	89.57 %	92.98 %	84.91 %	0.02 s	GPU @ 2.5 Ghz (C/C++)
108	3D-CVF at SPA		code	89.56 %	93.52 %	82.45 %	0.06 s	1 core @ 2.5 Ghz (C/C++)
J. Yoo, Y. Kim, J. Kim and J. Choi: 3D-CVF: Generating Joint Camera and LiDAR Features Using Cross-View Spatial Feature Fusion for 3D Object Detection. ECCV 2020.
109	OcTr			89.56 %	93.08 %	86.74 %	0.06 s	GPU @ 2.5 Ghz (Python + C/C++)
C. Zhou, Y. Zhang, J. Chen and D. Huang: OcTr: Octree-based Transformer for 3D Object Detection. CVPR 2023.
110	Struc info fusion II			89.54 %	95.26 %	82.31 %	0.05 s	GPU @ 2.5 Ghz (Python)
P. An, J. Liang, J. Ma, K. Yu and B. Fang: Struc info fusion. Submitted to CVIU 2021.
111	spark_second_focal_w			89.53 %	91.19 %	85.11 %	0.1 s	1 core @ 2.5 Ghz (Python)
ERROR: Wrong syntax in BIBTEX file.
112	spark_second		code	89.53 %	91.23 %	85.02 %	. s	1 core @ 2.5 Ghz (Python)
113	PSMS-Net			89.53 %	95.32 %	86.71 %	0.1 s	1 core @ 2.5 Ghz (C/C++)
114	IIOU		code	89.52 %	92.90 %	84.56 %	0.1 s	GPU @ 2.5 Ghz (Python + C/C++)
115	spark_pointpillar		code	89.51 %	93.58 %	85.03 %	0.02 s	GPU @ 2.5 Ghz (Python)
116	SASA		code	89.51 %	92.87 %	86.35 %	0.04 s	1 core @ 2.5 Ghz (Python + C/C++)
C. Chen, Z. Chen, J. Zhang and D. Tao: SASA: Semantics-Augmented Set Abstraction for Point-based 3D Object Detection. arXiv preprint arXiv:2201.01976 2022.
117	Fast-CLOCs			89.49 %	93.03 %	86.40 %	0.1 s	GPU @ 2.5 Ghz (Python)
S. Pang, D. Morris and H. Radha: Fast-CLOCs: Fast Camera-LiDAR Object Candidates Fusion for 3D Object Detection. Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) 2022.
118	IA-SSD (single)		code	89.48 %	93.14 %	84.42 %	0.013 s	1 core @ 2.5 Ghz (C/C++)
Y. Zhang, Q. Hu, G. Xu, Y. Ma, J. Wan and Y. Guo: Not All Points Are Equal: Learning Highly Efficient Point-based Detectors for 3D LiDAR Point Clouds. CVPR 2022.
119	KPTr			89.48 %	92.74 %	84.50 %	0.07 s	1 core @ 2.5 Ghz (C/C++)
ERROR: Wrong syntax in BIBTEX file.
120	CLOCs		code	89.48 %	92.91 %	86.42 %	0.1 s	1 core @ 2.5 Ghz (Python)
S. Pang, D. Morris and H. Radha: CLOCs: Camera-LiDAR Object Candidates Fusion for 3D Object Detection . 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) 2020.
121	PA3DNet			89.46 %	93.11 %	84.60 %	0.1 s	GPU @ 2.5 Ghz (Python + C/C++)
M. Wang, L. Zhao and Y. Yue: PA3DNet: 3-D Vehicle Detection with Pseudo Shape Segmentation and Adaptive Camera- LiDAR Fusion. IEEE Transactions on Industrial Informatics 2023.
122	PG-RCNN		code	89.46 %	93.39 %	86.54 %	0.06 s	GPU @ 1.5 Ghz (Python)
I. Koo, I. Lee, S. Kim, H. Kim, W. Jeon and C. Kim: PG-RCNN: Semantic Surface Point Generation for 3D Object Detection. 2023.
123	DFAF3D			89.45 %	93.14 %	84.22 %	0.05 s	1 core @ 2.5 Ghz (Python)
Q. Tang, X. Bai, J. Guo, B. Pan and W. Jiang: DFAF3D: A dual-feature-aware anchor-free single-stage 3D detector for point clouds. Image and Vision Computing 2023.
124	DVF-V			89.42 %	93.12 %	86.50 %	0.1 s	1 core @ 2.5 Ghz (C/C++)
A. Mahmoud, J. Hu and S. Waslander: Dense Voxel Fusion for 3D Object Detection. WACV 2023.
125	Struc info fusion I			89.38 %	94.91 %	84.29 %	0.05 s	1 core @ 2.5 Ghz (Python)
P. An, J. Liang, J. Ma, K. Yu and B. Fang: Struc info fusion. Submitted to CVIU 2021.
126	BtcDet		code	89.34 %	92.81 %	84.55 %	0.09 s	GPU @ 2.5 Ghz (Python + C/C++)
Q. Xu, Y. Zhong and U. Neumann: Behind the Curtain: Learning Occluded Shapes for 3D Object Detection. Proceedings of the AAAI Conference on Artificial Intelligence 2022.
127	IA-SSD (multi)		code	89.33 %	92.79 %	84.35 %	0.014 s	1 core @ 2.5 Ghz (C/C++)
Y. Zhang, Q. Hu, G. Xu, Y. Ma, J. Wan and Y. Guo: Not All Points Are Equal: Learning Highly Efficient Point-based Detectors for 3D LiDAR Point Clouds. CVPR 2022.
128	GSG-FPS		code	89.32 %	92.77 %	84.27 %	0.01 s	1 core @ 2.5 Ghz (C/C++)
129	spark_second2			89.27 %	90.94 %	84.85 %	10 s	1 core @ 2.5 Ghz (Python)
130	ACDet		code	89.21 %	92.87 %	85.80 %	0.05 s	1 core @ 2.5 Ghz (C/C++)
J. Xu, G. Wang, X. Zhang and G. Wan: ACDet: Attentive Cross-view Fusion for LiDAR-based 3D Object Detection. 3DV 2022.
131	DVF-PV			89.20 %	93.08 %	86.28 %	0.1 s	1 core @ 2.5 Ghz (C/C++)
A. Mahmoud, J. Hu and S. Waslander: Dense Voxel Fusion for 3D Object Detection. WACV 2023.
132	Test_dif		code	89.20 %	92.69 %	84.23 %	0.01 s	1 core @ 2.5 Ghz (C/C++)
133	STD		code	89.19 %	94.74 %	86.42 %	0.08 s	GPU @ 2.5 Ghz (Python + C/C++)
Z. Yang, Y. Sun, S. Liu, X. Shen and J. Jia: STD: Sparse-to-Dense 3D Object Detector for Point Cloud. ICCV 2019.
134	FIRM-Net			89.18 %	92.56 %	86.33 %	0.07 s	1 core @ 2.5 Ghz (Python)
135	Point-GNN		code	89.17 %	93.11 %	83.90 %	0.6 s	GPU @ 2.5 Ghz (Python)
W. Shi and R. Rajkumar: Point-GNN: Graph Neural Network for 3D Object Detection in a Point Cloud. CVPR 2020.
136	HMFI		code	89.17 %	93.04 %	86.37 %	0.1 s	1 core @ 2.5 Ghz (C/C++)
X. Li, B. Shi, Y. Hou, X. Wu, T. Ma, Y. Li and L. He: Homogeneous Multi-modal Feature Fusion and Interaction for 3D Object Detection. ECCV 2022.
137	sec_spark		code	89.16 %	90.89 %	84.84 %	0.03 s	GPU @ 2.5 Ghz (Python)
138	SSL-PointGNN		code	89.16 %	92.92 %	83.99 %	0.56 s	GPU @ 1.5 Ghz (Python)
E. Erçelik, E. Yurtsever, M. Liu, Z. Yang, H. Zhang, P. Topçam, M. Listl, Y. Çaylı and A. Knoll: 3D Object Detection with a Self-supervised Lidar Scene Flow Backbone. arXiv preprint arXiv:2205.00705 2022.
139	MMAE			89.15 %	92.42 %	84.01 %	0.07 s	1 core @ 2.5 Ghz (C/C++)
140	SPG_mini		code	89.12 %	92.80 %	86.27 %	0.09 s	GPU @ 2.5 Ghz (Python)
Q. Xu, Y. Zhou, W. Wang, C. Qi and D. Anguelov: SPG: Unsupervised Domain Adaptation for 3D Object Detection via Semantic Point Generation. Proceedings of the IEEE conference on computer vision and pattern recognition (ICCV) 2021.
141	EQ-PVRCNN		code	89.09 %	94.55 %	86.42 %	0.2 s	GPU @ 2.5 Ghz (Python + C/C++)
Z. Yang, L. Jiang, Y. Sun, B. Schiele and J. Jia: A Unified Query-based Paradigm for Point Cloud Understanding. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition 2022.
142	VoxSeT		code	89.07 %	92.70 %	86.29 %	33 ms	1 core @ 2.5 Ghz (C/C++)
C. He, R. Li, S. Li and L. Zhang: Voxel Set Transformer: A Set-to-Set Approach to 3D Object Detection from Point Clouds. CVPR 2022.
143	RAFDet			89.07 %	92.64 %	85.96 %	0.1 s	1 core @ 2.5 Ghz (C/C++)
144	RAFDet			89.05 %	92.29 %	84.35 %	0.01 s	1 core @ 2.5 Ghz (C/C++)
145	3DSSD		code	89.02 %	92.66 %	85.86 %	0.04 s	GPU @ 2.5 Ghz (Python + C/C++)
Z. Yang, Y. Sun, S. Liu and J. Jia: 3DSSD: Point-based 3D Single Stage Object Detector. CVPR 2020.
146	RagNet3D		code	89.01 %	92.87 %	86.36 %	0.05 s	1 core @ 2.5 Ghz (C/C++)
147	EPNet++			89.00 %	95.41 %	85.73 %	0.1 s	GPU @ 2.5 Ghz (Python)
Z. Liu, T. Huang, B. Li, X. Chen, X. Wang and X. Bai: EPNet++: Cascade Bi-Directional Fusion for Multi-Modal 3D Object Detection. IEEE Transactions on Pattern Analysis and Machine Intelligence 2022.
148	DDF			89.00 %	92.57 %	86.50 %	0.1 s	1 core @ 2.5 Ghz (Python)
149	IOUFusion			89.00 %	92.47 %	84.10 %	0.1 s	GPU @ 2.5 Ghz (Python)
150	Focals Conv		code	89.00 %	92.67 %	86.33 %	0.1 s	1 core @ 2.5 Ghz (C/C++)
Y. Chen, Y. Li, X. Zhang, J. Sun and J. Jia: Focal Sparse Convolutional Networks for 3D Object Detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition 2022.
151	RAFDet		code	88.99 %	92.23 %	84.21 %	0.01 s	1 core @ 2.5 Ghz (C/C++)
152	LGNet-Car		code	88.98 %	92.83 %	86.26 %	0.11 s	1 core @ 2.5 Ghz (Python + C/C++)
153	USVLab BSAODet		code	88.90 %	92.66 %	86.23 %	0.04 s	1 core @ 2.5 Ghz (C/C++)
W. Xiao, Y. Peng, C. Liu, J. Gao, Y. Wu and X. Li: Balanced Sample Assignment and Objective for Single-Model Multi-Class 3D Object Detection. IEEE Transactions on Circuits and Systems for Video Technology 2023.
154	bs			88.88 %	94.53 %	86.00 %	0.1 s	1 core @ 2.5 Ghz (C/C++)
155	CZY_PPF_Net			88.88 %	94.68 %	86.15 %	0.1 s	1 core @ 2.5 Ghz (C/C++)
156	H^23D R-CNN		code	88.87 %	92.85 %	86.07 %	0.03 s	1 core @ 2.5 Ghz (C/C++)
J. Deng, W. Zhou, Y. Zhang and H. Li: From Multi-View to Hollow-3D: Hallucinated Hollow-3D R-CNN for 3D Object Detection. IEEE Transactions on Circuits and Systems for Video Technology 2021.
157	Pyramid R-CNN			88.84 %	92.19 %	86.21 %	0.07 s	1 core @ 2.5 Ghz (C/C++)
J. Mao, M. Niu, H. Bai, X. Liang, H. Xu and C. Xu: Pyramid R-CNN: Towards Better Performance and Adaptability for 3D Object Detection. ICCV 2021.
158	CityBrainLab-CT3D		code	88.83 %	92.36 %	84.07 %	0.07 s	1 core @ 2.5 Ghz (Python + C/C++)
H. Sheng, S. Cai, Y. Liu, B. Deng, J. Huang, X. Hua and M. Zhao: Improving 3D Object Detection with Channel- wise Transformer. ICCV 2021.
159	Voxel R-CNN		code	88.83 %	94.85 %	86.13 %	0.04 s	GPU @ 3.0 Ghz (C/C++)
J. Deng, S. Shi, P. Li, W. Zhou, Y. Zhang and H. Li: Voxel R-CNN: Towards High Performance Voxel-based 3D Object Detection . AAAI 2021.
160	HVNet			88.82 %	92.83 %	83.38 %	0.03 s	GPU @ 2.0 Ghz (Python)
M. Ye, S. Xu and T. Cao: HVNet: Hybrid Voxel Network for LiDAR Based 3D Object Detection. CVPR 2020.
161	AMVFNet		code	88.82 %	92.68 %	86.18 %	0.04 s	GPU @ 2.5 Ghz (Python)
162	GD-MAE			88.82 %	94.22 %	83.54 %	0.07 s	1 core @ 2.5 Ghz (Python + C/C++)
H. Yang, T. He, J. Liu, H. Chen, B. Wu, B. Lin, X. He and W. Ouyang: GD-MAE: Generative Decoder for MAE Pre- training on LiDAR Point Clouds. CVPR 2023.
163	SPG		code	88.70 %	94.33 %	85.98 %	0.09 s	1 core @ 2.5 Ghz (Python + C/C++)
Q. Xu, Y. Zhou, W. Wang, C. Qi and D. Anguelov: SPG: Unsupervised Domain Adaptation for 3D Object Detection via Semantic Point Generation. Proceedings of the IEEE conference on computer vision and pattern recognition (ICCV) 2021.
164	MG			88.66 %	92.64 %	83.61 %	0.1 s	1 core @ 2.5 Ghz (C/C++)
165	SIENet		code	88.65 %	92.38 %	86.03 %	0.08 s	1 core @ 2.5 Ghz (Python)
Z. Li, Y. Yao, Z. Quan, W. Yang and J. Xie: SIENet: Spatial Information Enhancement Network for 3D Object Detection from Point Cloud. 2021.
166	P2V-RCNN			88.63 %	92.72 %	86.14 %	0.1 s	1 core @ 2.5 Ghz (C/C++)
J. Li, S. Luo, Z. Zhu, H. Dai, A. Krylov, Y. Ding and L. Shao: P2V-RCNN: Point to Voxel Feature Learning for 3D Object Detection from Point Clouds. IEEE Access 2021.
167	FromVoxelToPoint		code	88.61 %	92.23 %	86.11 %	0.1 s	1 core @ 2.5 Ghz (C/C++)
J. Li, H. Dai, L. Shao and Y. Ding: From Voxel to Point: IoU-guided 3D Object Detection for Point Cloud with Voxel-to- Point Decoder. MM '21: The 29th ACM International Conference on Multimedia (ACM MM) 2021.
168	RangeIoUDet			88.59 %	92.28 %	85.83 %	0.02 s	GPU @ 2.5 Ghz (Python + C/C++)
Z. Liang, Z. Zhang, M. Zhang, X. Zhao and S. Pu: RangeIoUDet: Range Image Based Real-Time 3D Object Detector Optimized by Intersection Over Union. CVPR 2021.
169	af			88.58 %	92.43 %	86.05 %	1 s	GPU @ 2.5 Ghz (Python)
170	RBEV-Voxel		code	88.54 %	91.92 %	85.73 %	0.08 s	GPU @ 2.5 Ghz (Python)
171	MFB3D			88.54 %	94.67 %	85.75 %	0.14 s	1 core @ 2.5 Ghz (Python)
172	second_iou_baseline		code	88.48 %	92.24 %	85.57 %	0.05 s	1 core @ 2.5 Ghz (Python)
173	EPNet		code	88.47 %	94.22 %	83.69 %	0.1 s	1 core @ 2.5 Ghz (Python + C/C++)
T. Huang, Z. Liu, X. Chen and X. Bai: EPNet: Enhancing Point Features with Image Semantics for 3D Object Detection. ECCV 2020.
174	CenterNet3D			88.46 %	91.80 %	83.62 %	0.04 s	GPU @ 1.5 Ghz (Python)
G. Wang, B. Tian, Y. Ai, T. Xu, L. Chen and D. Cao: CenterNet3D:An Anchor free Object Detector for Autonomous Driving. 2020.
175	FARP-Net		code	88.45 %	91.20 %	86.01 %	0.06 s	GPU @ 2.5 Ghz (Python + C/C++)
T. Xie, L. Wang, K. Wang, R. Li, X. Zhang, H. Zhang, L. Yang, H. Liu and J. Li: FARP-Net: Local-Global Feature Aggregation and Relation-Aware Proposals for 3D Object Detection. IEEE Transactions on Multimedia 2023.
176	PUDet			88.42 %	92.68 %	83.70 %	0.3 s	GPU @ 2.5 Ghz (Python)
177	RangeRCNN			88.40 %	92.15 %	85.74 %	0.06 s	GPU @ 2.5 Ghz (Python + C/C++)
Z. Liang, M. Zhang, Z. Zhang, X. Zhao and S. Pu: RangeRCNN: Towards Fast and Accurate 3D Object Detection with Range Image Representation. arXiv preprint arXiv:2009.00206 2020.
178	second_iou_baseline			88.40 %	92.12 %	85.54 %	0.03 s	1 core @ 2.5 Ghz (Python)
179	Patches			88.39 %	92.72 %	83.19 %	0.15 s	GPU @ 2.0 Ghz
J. Lehner, A. Mitterecker, T. Adler, M. Hofmarcher, B. Nessler and S. Hochreiter: Patch Refinement: Localized 3D Object Detection. arXiv preprint arXiv:1910.04093 2019.
180	3D IoU-Net			88.38 %	94.76 %	81.93 %	0.1 s	1 core @ 2.5 Ghz (C/C++)
J. Li, S. Luo, Z. Zhu, H. Dai, S. Krylov, Y. Ding and L. Shao: 3D IoU-Net: IoU Guided 3D Object Detector for Point Clouds. arXiv preprint arXiv:2004.04962 2020.
181	StructuralIF			88.38 %	91.78 %	85.67 %	0.02 s	8 cores @ 2.5 Ghz (Python)
J. Pei An: Deep structural information fusion for 3D object detection on LiDAR-camera system. Accepted in CVIU 2021.
182	PASS-PV-RCNN-Plus			88.37 %	92.17 %	85.75 %	1 s	1 core @ 2.5 Ghz (Python)
Anonymous: Leveraging Anchor-based LiDAR 3D Object Detection via Point Assisted Sample Selection. will submit to computer vision conference/journal 2024.
183	AAMVFNet		code	88.36 %	92.31 %	85.81 %	0.04 s	GPU @ 2.5 Ghz (Python)
184	CLOCs_SecCas			88.23 %	91.16 %	82.63 %	0.1 s	1 core @ 2.5 Ghz (Python)
S. Pang, D. Morris and H. Radha: CLOCs: Camera-LiDAR Object Candidates Fusion for 3D Object Detection. 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) 2020.
185	UberATG-MMF			88.21 %	93.67 %	81.99 %	0.08 s	GPU @ 2.5 Ghz (Python)
M. Liang*, B. Yang*, Y. Chen, R. Hu and R. Urtasun: Multi-Task Multi-Sensor Fusion for 3D Object Detection. CVPR 2019.
186	MMpointpillars			88.17 %	91.76 %	81.13 %	0.05 s	1 core @ 2.5 Ghz (Python)
187	Patches - EMP			88.17 %	94.49 %	84.75 %	0.5 s	GPU @ 2.5 Ghz (Python)
J. Lehner, A. Mitterecker, T. Adler, M. Hofmarcher, B. Nessler and S. Hochreiter: Patch Refinement: Localized 3D Object Detection. arXiv preprint arXiv:1910.04093 2019.
188	SRDL			88.17 %	92.01 %	85.43 %	0.05 s	1 core @ 2.5 Ghz (Python + C/C++)
ERROR: Wrong syntax in BIBTEX file.
189	Res3DNet			88.16 %	91.71 %	84.85 %	0.05 s	GPU @ 3.5 Ghz (Python)
190	P2P		code	88.15 %	91.92 %	81.12 %	0.1 s	GPU @ 2.5 Ghz (Python + C/C++)
191	PointPainting			88.11 %	92.45 %	83.36 %	0.4 s	GPU @ 2.5 Ghz (Python + C/C++)
S. Vora, A. Lang, B. Helou and O. Beijbom: PointPainting: Sequential Fusion for 3D Object Detection. CVPR 2020.
192	SERCNN			88.10 %	94.11 %	83.43 %	0.1 s	1 core @ 2.5 Ghz (Python)
D. Zhou, J. Fang, X. Song, L. Liu, J. Yin, Y. Dai, H. Li and R. Yang: Joint 3D Instance Segmentation and Object Detection for Autonomous Driving. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition 2020.
193	PartA2_basline		code	88.09 %	92.35 %	85.42 %	0.09 s	1 core @ 2.5 Ghz (Python)
194	Associate-3Ddet		code	88.09 %	91.40 %	82.96 %	0.05 s	1 core @ 2.5 Ghz (Python + C/C++)
L. Du, X. Ye, X. Tan, J. Feng, Z. Xu, E. Ding and S. Wen: Associate-3Ddet: Perceptual-to-Conceptual Association for 3D Point Cloud Object Detection. The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2020.
195	HotSpotNet			88.09 %	94.06 %	83.24 %	0.04 s	1 core @ 2.5 Ghz (Python + C/C++)
Q. Chen, L. Sun, Z. Wang, K. Jia and A. Yuille: object as hotspots. Proceedings of the European Conference on Computer Vision (ECCV) 2020.
196	Faraway-Frustum		code	88.08 %	91.90 %	85.35 %	0.1 s	GPU @ 2.5 Ghz (Python)
H. Zhang, D. Yang, E. Yurtsever, K. Redmill and U. Ozguner: Faraway-frustum: Dealing with lidar sparsity for 3D object detection using fusion. 2021 IEEE International Intelligent Transportation Systems Conference (ITSC) 2021.
197	SFEBEV			88.08 %	93.44 %	83.01 %	0.01 s	1 core @ 2.5 Ghz (C/C++)
198	pointpillar_spark_fo			88.02 %	92.48 %	84.82 %	0.1 s	1 core @ 2.5 Ghz (C/C++)
ERROR: Wrong syntax in BIBTEX file.
199	UberATG-HDNET			87.98 %	93.13 %	81.23 %	0.05 s	GPU @ 2.5 Ghz (Python)
B. Yang, M. Liang and R. Urtasun: HDNET: Exploiting HD Maps for 3D Object Detection. 2nd Conference on Robot Learning (CoRL) 2018.
200	spark_pointpillar2			87.93 %	92.74 %	84.70 %	10 s	1 core @ 2.5 Ghz (Python)
201	BAPartA2S-4h			87.89 %	91.96 %	83.31 %	0.1 s	1 core @ 2.5 Ghz (Python)
202	Fast Point R-CNN			87.84 %	90.87 %	80.52 %	0.06 s	GPU @ 2.5 Ghz (Python + C/C++)
Y. Chen, S. Liu, X. Shen and J. Jia: Fast Point R-CNN. Proceedings of the IEEE international conference on computer vision (ICCV) 2019.
203	MMLab-PartA^2		code	87.79 %	91.70 %	84.61 %	0.08 s	GPU @ 2.5 Ghz (Python + C/C++)
S. Shi, Z. Wang, J. Shi, X. Wang and H. Li: From Points to Parts: 3D Object Detection from Point Cloud with Part-aware and Part-aggregation Network. IEEE Transactions on Pattern Analysis and Machine Intelligence 2020.
204	SIF			87.76 %	91.44 %	85.15 %	0.1 s	1 core @ 2.5 Ghz (C/C++)
P. An: SIF. Submitted to CVIU 2021.
205	MVAF-Net		code	87.73 %	91.95 %	85.00 %	0.06 s	1 core @ 2.5 Ghz (Python + C/C++)
G. Wang, B. Tian, Y. Zhang, L. Chen, D. Cao and J. Wu: Multi-View Adaptive Fusion Network for 3D Object Detection. arXiv preprint arXiv:2011.00652 2020.
206	DVFENet			87.68 %	90.93 %	84.60 %	0.05 s	1 core @ 2.5 Ghz (Python + C/C++)
Y. He, G. Xia, Y. Luo, L. Su, Z. Zhang, W. Li and P. Wang: DVFENet: Dual-branch Voxel Feature Extraction Network for 3D Object Detection. Neurocomputing 2021.
207	S-AT GCN			87.68 %	90.85 %	84.20 %	0.02 s	GPU @ 2.0 Ghz (Python)
L. Wang, C. Wang, X. Zhang, T. Lan and J. Li: S-AT GCN: Spatial-Attention Graph Convolution Network based Feature Enhancement for 3D Object Detection. CoRR 2021.
208	RangeDet (Official)		code	87.67 %	90.93 %	82.92 %	0.02 s	1 core @ 2.5 Ghz (C/C++)
L. Fan, X. Xiong, F. Wang, N. Wang and Z. Zhang: RangeDet: In Defense of Range View for LiDAR-Based 3D Object Detection. Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) 2021.
209	pointpillar_baseline		code	87.61 %	92.52 %	83.84 %	0.01 s	1 core @ 2.5 Ghz (Python)
210	Second_baseline		code	87.60 %	90.94 %	84.36 %	0.03 s	1 core @ 2.5 Ghz (Python)
211	VoxelFSD-S			87.60 %	90.94 %	84.11 %	0.05 s	1 core @ 2.5 Ghz (C/C++)
212	U_second_v4_ep_100_8			87.58 %	90.54 %	84.34 %	0.1 s	1 core @ 2.5 Ghz (C/C++)
213	SC-SSD			87.56 %	90.70 %	84.36 %	1 s	1 core @ 2.5 Ghz (C/C++)
214	MODet			87.56 %	90.80 %	82.69 %	0.05 s	GTX1080Ti
Y. Zhang, Z. Xiang, C. Qiao and S. Chen: Accurate and Real-Time Object Detection Based on Bird's Eye View on 3D Point Clouds. 2019 International Conference on 3D Vision (3DV) 2019.
215	TF-PartA2			87.54 %	91.93 %	83.33 %	0.1 s	1 core @ 2.5 Ghz (Python + C/C++)
216	AB3DMOT		code	87.53 %	91.99 %	81.03 %	0.0047s	1 core @ 2.5 Ghz (Python)
X. Weng and K. Kitani: A Baseline for 3D Multi-Object Tracking. arXiv:1907.03961 2019.
217	mm3d_PartA2			87.51 %	91.75 %	83.01 %	0.1 s	GPU @ >3.5 Ghz (Python)
218	SeSame-point		code	87.49 %	90.84 %	83.77 %	N/A s	TITAN RTX @ 1.35 Ghz (Python)
219	PointRGCN			87.49 %	91.63 %	80.73 %	0.26 s	GPU @ V100 (Python)
J. Zarzar, S. Giancola and B. Ghanem: PointRGCN: Graph Convolution Networks for 3D Vehicles Detection Refinement. ArXiv 2019.
220	MGAF-3DSSD		code	87.47 %	92.70 %	82.19 %	0.1 s	1 core @ 2.5 Ghz (Python)
J. Li, H. Dai, L. Shao and Y. Ding: Anchor-free 3D Single Stage Detector with Mask-Guided Attention for Point Cloud. MM '21: The 29th ACM International Conference on Multimedia (ACM MM) 2021.
221	PC-CNN-V2			87.40 %	91.19 %	79.35 %	0.5 s	GPU @ 2.5 Ghz (Matlab + C/C++)
X. Du, M. Ang, S. Karaman and D. Rus: A General Pipeline for 3D Detection of Vehicles. 2018 IEEE International Conference on Robotics and Automation (ICRA) 2018.
222	MMLab-PointRCNN		code	87.39 %	92.13 %	82.72 %	0.1 s	GPU @ 2.5 Ghz (Python + C/C++)
S. Shi, X. Wang and H. Li: Pointrcnn: 3d object proposal generation and detection from point cloud. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition 2019.
223	Sem-Aug			87.37 %	93.35 %	82.43 %	0.1 s	GPU @ 2.5 Ghz (Python)
L. Zhao, M. Wang and Y. Yue: Sem-Aug: Improving Camera-LiDAR Feature Fusion With Semantic Augmentation for 3D Vehicle Detection. IEEE Robotics and Automation Letters 2022.
224	MAFF-Net(DAF-Pillar)			87.34 %	90.79 %	77.66 %	0.04 s	1 core @ 2.5 Ghz (Python + C/C++)
Z. Zhang, Z. Liang, M. Zhang, X. Zhao, Y. Ming, T. Wenming and S. Pu: MAFF-Net: Filter False Positive for 3D Vehicle Detection with Multi-modal Adaptive Feature Fusion. arXiv preprint arXiv:2009.10945 2020.
225	Harmonic PointPillar		code	87.28 %	90.89 %	82.54 %	0.01 s	1 core @ 2.5 Ghz (Python)
H. Zhang, J. Mekala, Z. Nain, J. Park and H. Jung: 3D Harmonic Loss: Towards Task-consistent and Time-friendly 3D Object Detection for V2X Orchestration. will submit to IEEE Transactions on Vehicular Technology 2022.
226	PASS-PointPillar			87.23 %	91.07 %	81.98 %	1 s	1 core @ 2.5 Ghz (C/C++)
Anonymous: Leveraging Anchor-based LiDAR 3D Object Detection via Point Assisted Sample Selection. will submit to computer vision conference/journal 2024.
227	HRI-VoxelFPN			87.21 %	92.75 %	79.82 %	0.02 s	GPU @ 2.5 Ghz (Python + C/C++)
H. Kuang, B. Wang, J. An, M. Zhang and Z. Zhang: Voxel-FPN:multi-scale voxel feature aggregation in 3D object detection from point clouds. sensors 2020.
228	epBRM		code	87.13 %	90.70 %	81.92 %	0.1 s	GPU @ >3.5 Ghz (Python + C/C++)
K. Shin: Improving a Quality of 3D Object Detection by Spatial Transformation Mechanism. arXiv preprint arXiv:1910.04853 2019.
229	LVFSD			87.12 %	90.42 %	83.91 %	0.06 s
ERROR: Wrong syntax in BIBTEX file.
230	XT-PartA2			87.08 %	90.89 %	82.70 %	0.1 s	GPU @ >3.5 Ghz (Python)
231	centerpoint_pcdet			87.04 %	90.04 %	83.32 %	0.06 s	1 core @ 2.5 Ghz (Python)
232	SARPNET			86.92 %	92.21 %	81.68 %	0.05 s	1 core @ 2.5 Ghz (Python + C/C++)
Y. Ye, H. Chen, C. Zhang, X. Hao and Z. Zhang: SARPNET: Shape Attention Regional Proposal Network for LiDAR-based 3D Object Detection. Neurocomputing 2019.
233	SeSame-pillar		code	86.88 %	90.61 %	81.93 %	N/A s	TITAN RTX @ 1.35 Ghz (Python)
234	ARPNET			86.81 %	90.06 %	79.41 %	0.08 s	GPU @ 2.5 Ghz (Python + C/C++)
Y. Ye, C. Zhang and X. Hao: ARPNET: attention region proposal network for 3D object detection. Science China Information Sciences 2019.
235	C-GCN			86.78 %	91.11 %	80.09 %	0.147 s	GPU @ V100 (Python)
J. Zarzar, S. Giancola and B. Ghanem: PointRGCN: Graph Convolution Networks for 3D Vehicles Detection Refinement. ArXiv 2019.
236	PointPillars		code	86.56 %	90.07 %	82.81 %	16 ms	1080ti GPU and Intel i7 CPU
A. Lang, S. Vora, H. Caesar, L. Zhou, J. Yang and O. Beijbom: PointPillars: Fast Encoders for Object Detection from Point Clouds. CVPR 2019.
237	TANet		code	86.54 %	91.58 %	81.19 %	0.035s	GPU @ 2.5 Ghz (Python + C/C++)
Z. Liu, X. Zhao, T. Huang, R. Hu, Y. Zhou and X. Bai: TANet: Robust 3D Object Detection from Point Clouds with Triple Attention. AAAI 2020.
238	PCNet3D			86.54 %	90.09 %	81.43 %	0.05 s	GPU @ 3.5 Ghz (Python)
239	MEDL-U			86.50 %	91.75 %	79.29 %	1 s	GPU @ >3.5 Ghz (Python)
240	SCNet			86.48 %	90.07 %	81.30 %	0.04 s	GPU @ 3.0 Ghz (Python)
Z. Wang, H. Fu, L. Wang, L. Xiao and B. Dai: SCNet: Subdivision Coding Network for Object Detection Based on 3D Point Cloud. IEEE Access 2019.
241	MM_SECOND		code	86.39 %	90.52 %	81.49 %	0.05 s	GPU @ >3.5 Ghz (Python)
242	SegVoxelNet			86.37 %	91.62 %	83.04 %	0.04 s	1 core @ 2.5 Ghz (Python)
H. Yi, S. Shi, M. Ding, J. Sun, K. Xu, H. Zhou, Z. Wang, S. Li and G. Wang: SegVoxelNet: Exploring Semantic Context and Depth-aware Features for 3D Vehicle Detection from Point Cloud. ICRA 2020.
243	IIOU_LDR		code	86.31 %	91.80 %	81.30 %	0.03 s	1 core @ 2.5 Ghz (C/C++)
244	3D IoU Loss			86.22 %	91.36 %	81.20 %	0.08 s	GPU @ 2.5 Ghz (Python + C/C++)
D. Zhou, J. Fang, X. Song, C. Guan, J. Yin, Y. Dai and R. Yang: IoU Loss for 2D/3D Object Detection. International Conference on 3D Vision (3DV) 2019.
245	VSAC			86.22 %	91.98 %	81.50 %	0.07 s	1 core @ 1.0 Ghz (Python)
ERROR: Wrong syntax in BIBTEX file.
246	prcnn_v18_80_100			86.20 %	90.79 %	81.39 %	0.1 s	1 core @ 2.5 Ghz (Python)
247	voxelnext_pcdet			86.15 %	89.72 %	82.34 %	0.05 s	1 core @ 2.5 Ghz (Python)
248	ROT_S3D			86.11 %	91.33 %	81.17 %	0.1 s	GPU @ 2.5 Ghz (Python)
249	SeSame-pillar w/scor		code	86.11 %	90.43 %	81.38 %	N/A s	1 core @ 2.5 Ghz (C/C++)
250	R-GCN			86.05 %	91.91 %	81.05 %	0.16 s	GPU @ 2.5 Ghz (Python)
J. Zarzar, S. Giancola and B. Ghanem: PointRGCN: Graph Convolution Networks for 3D Vehicles Detection Refinement. ArXiv 2019.
251	UberATG-PIXOR++			86.01 %	93.28 %	80.11 %	0.035 s	GPU @ 2.5 Ghz (Python)
B. Yang, M. Liang and R. Urtasun: HDNET: Exploiting HD Maps for 3D Object Detection. 2nd Conference on Robot Learning (CoRL) 2018.
252	HINTED			86.01 %	90.61 %	79.29 %	0.04 s	1 core @ 2.5 Ghz (C/C++)
253	CAT2			85.90 %	91.13 %	80.81 %	1 s	1 core @ 2.5 Ghz (C/C++)
254	Sem-Aug-PointRCNN++			85.88 %	91.68 %	83.37 %	0.1 s	8 cores @ 3.0 Ghz (Python)
L. Zhao, M. Wang and Y. Yue: Sem-Aug: Improving Camera-LiDAR Feature Fusion With Semantic Augmentation for 3D Vehicle Detection. IEEE Robotics and Automation Letters 2022.
255	DASS			85.85 %	91.74 %	80.97 %	0.09 s	1 core @ 2.0 Ghz (Python)
O. Unal, L. Van Gool and D. Dai: Improving Point Cloud Semantic Segmentation by Learning 3D Object Detection. Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) 2021.
256	F-ConvNet		code	85.84 %	91.51 %	76.11 %	0.47 s	GPU @ 2.5 Ghz (Python + C/C++)
Z. Wang and K. Jia: Frustum ConvNet: Sliding Frustums to Aggregate Local Point-Wise Features for Amodal 3D Object Detection. IROS 2019.
257	SecAtten			85.84 %	91.32 %	82.57 %	0.1 s	1 core @ 2.5 Ghz (C/C++)
258	PI-RCNN			85.81 %	91.44 %	81.00 %	0.1 s	1 core @ 2.5 Ghz (Python)
L. Xie, C. Xiang, Z. Yu, G. Xu, Z. Yang, D. Cai and X. He: PI-RCNN: An Efficient Multi-sensor 3D Object Detector with Point-based Attentive Cont-conv Fusion Module. AAAI 2020 : The Thirty-Fourth AAAI Conference on Artificial Intelligence 2020.
259	PointRGBNet			85.73 %	91.39 %	80.68 %	0.08 s	4 cores @ 2.5 Ghz (Python + C/C++)
P. Xie Desheng: Real-time Detection of 3D Objects Based on Multi-Sensor Information Fusion. Automotive Engineering 2022.
260	SeSame-voxel		code	85.62 %	89.86 %	80.95 %	N/A s	TITAN RTX @ 1.35 Ghz (Python)
261	WA			85.61 %	90.76 %	79.99 %	0.3 s	GPU @ 2.5 Ghz (Python + C/C++)
262	UberATG-ContFuse			85.35 %	94.07 %	75.88 %	0.06 s	GPU @ 2.5 Ghz (Python)
M. Liang, B. Yang, S. Wang and R. Urtasun: Deep Continuous Fusion for Multi-Sensor 3D Object Detection. ECCV 2018.
263	PFF3D		code	85.08 %	89.61 %	80.42 %	0.05 s	GPU @ 3.0 Ghz (Python + C/C++)
L. Wen and K. Jo: Fast and Accurate 3D Object Detection for Lidar-Camera-Based Autonomous Vehicles Using One Shared Voxel-Based Backbone. IEEE Access 2021.
264	AVOD		code	84.95 %	89.75 %	78.32 %	0.08 s	Titan X (pascal)
J. Ku, M. Mozifian, J. Lee, A. Harakeh and S. Waslander: Joint 3D Proposal Generation and Object Detection from View Aggregation. IROS 2018.
265	WS3D			84.93 %	90.96 %	77.96 %	0.1 s	GPU @ 2.5 Ghz (Python)
Q. Meng, W. Wang, T. Zhou, J. Shen, L. Van Gool and D. Dai: Weakly Supervised 3D Object Detection from Lidar Point Cloud. 2020.
266	PI-SECOND		code	84.83 %	90.15 %	79.86 %	0.05 s	GPU @ >3.5 Ghz (Python + C/C++)
267	ODGS			84.82 %	89.59 %	78.20 %	0.1 s	1 core @ 2.5 Ghz (C/C++)
268	AVOD-FPN		code	84.82 %	90.99 %	79.62 %	0.1 s	Titan X (Pascal)
J. Ku, M. Mozifian, J. Lee, A. Harakeh and S. Waslander: Joint 3D Proposal Generation and Object Detection from View Aggregation. IROS 2018.
269	F-PointNet		code	84.67 %	91.17 %	74.77 %	0.17 s	GPU @ 3.0 Ghz (Python)
C. Qi, W. Liu, C. Wu, H. Su and L. Guibas: Frustum PointNets for 3D Object Detection from RGB-D Data. arXiv preprint arXiv:1711.08488 2017.
270	AEPF			84.63 %	89.99 %	80.02 %	0.05 s	GPU @ 2.5 Ghz (Python)
271	mmFUSION		code	84.60 %	90.35 %	79.82 %	1s	1 core @ 2.5 Ghz (Python)
J. Ahmad and A. Del Bue: mmFUSION: Multimodal Fusion for 3D Objects Detection. arXiv preprint arXiv:2311.04058 2023.
272	3DBN			83.94 %	89.66 %	76.50 %	0.13s	1080Ti (Python+C/C++)
X. Li, J. Guivant, N. Kwok and Y. Xu: 3D Backbone Network for 3D Object Detection. CoRR 2019.
273	EOTL		code	83.14 %	89.10 %	71.41 %	TBD s	1 core @ 2.5 Ghz (Python + C/C++)
R. Yang, Z. Yan, T. Yang, Y. Wang and Y. Ruichek: Efficient Online Transfer Learning for Road Participants Detection in Autonomous Driving. IEEE Sensors Journal 2023.
274	MLOD		code	82.68 %	90.25 %	77.97 %	0.12 s	GPU @ 1.5 Ghz (Python)
J. Deng and K. Czarnecki: MLOD: A multi-view 3D object detection based on robust feature fusion method. arXiv preprint arXiv:1909.04163 2019.
275	BirdNet+		code	81.85 %	87.43 %	75.36 %	0.11 s	Titan Xp (PyTorch)
A. Barrera, J. Beltrán, C. Guindel, J. Iglesias and F. García: BirdNet+: Two-Stage 3D Object Detection in LiDAR through a Sparsity-Invariant Bird’s Eye View. IEEE Access 2021.
276	DMF			80.29 %	84.64 %	76.05 %	0.2 s	1 core @ 2.5 Ghz (Python + C/C++)
X. J. Chen and W. Xu: Disparity-Based Multiscale Fusion Network for Transportation Detection. IEEE Transactions on Intelligent Transportation Systems 2022.
277	UberATG-PIXOR			80.01 %	83.97 %	74.31 %	0.035 s	TITAN Xp (Python)
B. Yang, W. Luo and R. Urtasun: PIXOR: Real-time 3D Object Detection from Point Clouds. CVPR 2018.
278	MV3D (LIDAR)			78.98 %	86.49 %	72.23 %	0.24 s	GPU @ 2.5 Ghz (Python + C/C++)
X. Chen, H. Ma, J. Wan, B. Li and T. Xia: Multi-View 3D Object Detection Network for Autonomous Driving. CVPR 2017.
279	DSGN++		code	78.94 %	88.55 %	69.74 %	0.2 s	GeForce RTX 2080Ti
Y. Chen, S. Huang, S. Liu, B. Yu and J. Jia: DSGN++: Exploiting Visual-Spatial Relation for Stereo-Based 3D Detectors. IEEE Transactions on Pattern Analysis and Machine Intelligence 2022.
280	MV3D			78.93 %	86.62 %	69.80 %	0.36 s	GPU @ 2.5 Ghz (Python + C/C++)
X. Chen, H. Ma, J. Wan, B. Li and T. Xia: Multi-View 3D Object Detection Network for Autonomous Driving. CVPR 2017.
281	StereoDistill			78.59 %	89.03 %	69.34 %	0.4 s	1 core @ 2.5 Ghz (Python)
Z. Liu, X. Ye, X. Tan, D. Errui, Y. Zhou and X. Bai: StereoDistill: Pick the Cream from LiDAR for Distilling Stereo-based 3D Object Detection. Proceedings of the AAAI Conference on Artificial Intelligence 2023.
282	MMLAB LIGA-Stereo		code	76.78 %	88.15 %	67.40 %	0.4 s	1 core @ 2.5 Ghz (Python + C/C++)
X. Guo, S. Shi, X. Wang and H. Li: LIGA-Stereo: Learning LiDAR Geometry Aware Representations for Stereo-based 3D Detector. Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) 2021.
283	RCD			75.83 %	82.26 %	69.61 %	0.1 s	GPU @ 2.5 Ghz (Python)
A. Bewley, P. Sun, T. Mensink, D. Anguelov and C. Sminchisescu: Range Conditioned Dilated Convolutions for Scale Invariant 3D Object Detection. Conference on Robot Learning (CoRL) 2020.
284	LaserNet			74.52 %	79.19 %	68.45 %	12 ms	GPU @ 2.5 Ghz (C/C++)
G. Meyer, A. Laddha, E. Kee, C. Vallespi-Gonzalez and C. Wellington: LaserNet: An Efficient Probabilistic 3D Object Detector for Autonomous Driving. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2019.
285	PL++ (SDN+GDC)		code	73.80 %	84.61 %	65.59 %	0.6 s	GPU @ 2.5 Ghz (C/C++)
Y. You, Y. Wang, W. Chao, D. Garg, G. Pleiss, B. Hariharan, M. Campbell and K. Weinberger: Pseudo-LiDAR++: Accurate Depth for 3D Object Detection in Autonomous Driving. International Conference on Learning Representations 2020.
286	SNVC		code	73.61 %	86.88 %	64.49 %	1 s	GPU @ 1.0 Ghz (Python)
S. Li, Z. Liu, Z. Shen and K. Cheng: Stereo Neural Vernier Caliper. Proceedings of the AAAI Conference on Artificial Intelligence 2022.
287	A3DODWTDA		code	73.26 %	79.58 %	62.77 %	0.08 s	GPU @ 3.0 Ghz (Python)
F. Gustafsson and E. Linder-Norén: Automotive 3D Object Detection Without Target Domain Annotations. 2018.
288	Complexer-YOLO			68.96 %	77.24 %	64.95 %	0.06 s	GPU @ 3.5 Ghz (C/C++)
M. Simon, K. Amende, A. Kraus, J. Honer, T. Samann, H. Kaulbersch, S. Milz and H. Michael Gross: Complexer-YOLO: Real-Time 3D Object Detection and Tracking on Semantic Point Clouds. The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops 2019.
289	TopNet-Retina			68.16 %	80.16 %	63.43 %	52ms	GeForce 1080Ti (tensorflow-gpu, v1.12)
S. Wirges, T. Fischer, C. Stiller and J. Frias: Object Detection and Classification in Occupancy Grid Maps Using Deep Convolutional Networks. 2018 21st International Conference on Intelligent Transportation Systems (ITSC) 2018.
290	SeSame-point w/score		code	67.18 %	83.44 %	57.68 %	N/A s	GPU @ 1.5 Ghz (Python)
291	CG-Stereo			66.44 %	85.29 %	58.95 %	0.57 s	GeForce RTX 2080 Ti
C. Li, J. Ku and S. Waslander: Confidence Guided Stereo 3D Object Detection with Split Depth Estimation. IROS 2020.
292	PLUME			66.27 %	82.97 %	56.70 %	0.15 s	GPU @ 2.5 Ghz (Python)
Y. Wang, B. Yang, R. Hu, M. Liang and R. Urtasun: PLUME: Efficient 3D Object Detection from Stereo Images. IROS 2021.
293	CDN		code	66.24 %	83.32 %	57.65 %	0.6 s	GPU @ 2.5 Ghz (Python)
D. Garg, Y. Wang, B. Hariharan, M. Campbell, K. Weinberger and W. Chao: Wasserstein Distances for Stereo Disparity Estimation. Advances in Neural Information Processing Systems (NeurIPS) 2020.
294	DSGN		code	65.05 %	82.90 %	56.60 %	0.67 s	NVIDIA Tesla V100
Y. Chen, S. Liu, X. Shen and J. Jia: DSGN: Deep Stereo Geometry Network for 3D Object Detection. CVPR 2020.
295	TopNet-DecayRate			64.60 %	79.74 %	58.04 %	92 ms	NVIDIA GeForce 1080 Ti (tensorflow-gpu)
S. Wirges, T. Fischer, C. Stiller and J. Frias: Object Detection and Classification in Occupancy Grid Maps Using Deep Convolutional Networks. 2018 21st International Conference on Intelligent Transportation Systems (ITSC) 2018.
296	SeSame-voxel w/score		code	63.36 %	71.98 %	57.52 %	N/A s	GPU @ 1.5 Ghz (Python)
297	BirdNet+ (legacy)		code	63.33 %	84.80 %	61.23 %	0.1 s	Titan Xp (PyTorch)
A. Barrera, C. Guindel, J. Beltrán and F. García: BirdNet+: End-to-End 3D Object Detection in LiDAR Bird’s Eye View. 2020 IEEE 23rd International Conference on Intelligent Transportation Systems (ITSC) 2020.
298	3D FCN			61.67 %	70.62 %	55.61 %	>5 s	1 core @ 2.5 Ghz (C/C++)
B. Li: 3D Fully Convolutional Network for Vehicle Detection in Point Cloud. IROS 2017.
299	CDN-PL++			61.04 %	81.27 %	52.84 %	0.4 s	GPU @ 2.5 Ghz (C/C++)
D. Garg, Y. Wang, B. Hariharan, M. Campbell, K. Weinberger and W. Chao: Wasserstein Distances for Stereo Disparity Estimation. Advances in Neural Information Processing Systems 2020.
300	BirdNet			59.83 %	84.17 %	57.35 %	0.11 s	Titan Xp (Caffe)
J. Beltrán, C. Guindel, F. Moreno, D. Cruzado, F. García and A. Escalera: BirdNet: A 3D Object Detection Framework from LiDAR Information. 2018 21st International Conference on Intelligent Transportation Systems (ITSC) 2018.
301	TopNet-UncEst			59.67 %	72.05 %	51.67 %	0.09 s	NVIDIA GeForce 1080 Ti (tensorflow-gpu)
S. Wirges, M. Braun, M. Lauer and C. Stiller: Capturing Object Detection Uncertainty in Multi-Layer Grid Maps. 2019.
302	RT3D-GMP			59.00 %	69.14 %	45.49 %	0.06 s	GPU @ 2.5 Ghz (Python + C/C++)
H. Königshof and C. Stiller: Learning-Based Shape Estimation with Grid Map Patches for Realtime 3D Object Detection for Automated Driving. 2020 IEEE 23rd International Conference on Intelligent Transportation Systems (ITSC) 2020.
303	Disp R-CNN (velo)		code	58.62 %	79.76 %	47.73 %	0.387 s	GPU @ 2.5 Ghz (Python + C/C++)
J. Sun, L. Chen, Y. Xie, S. Zhang, Q. Jiang, X. Zhou and H. Bao: Disp R-CNN: Stereo 3D Object Detection via Shape Prior Guided Instance Disparity Estimation. CVPR 2020.
304	ESGN			58.12 %	78.10 %	49.28 %	0.06 s	GPU @ 2.5 Ghz (Python + C/C++)
A. Gao, Y. Pang, J. Nie, Z. Shao, J. Cao, Y. Guo and X. Li: ESGN: Efficient Stereo Geometry Network for Fast 3D Object Detection. IEEE Transactions on Circuits and Systems for Video Technology 2022.
305	Pseudo-LiDAR++		code	58.01 %	78.31 %	51.25 %	0.4 s	GPU @ 2.5 Ghz (Python)
Y. You, Y. Wang, W. Chao, D. Garg, G. Pleiss, B. Hariharan, M. Campbell and K. Weinberger: Pseudo-LiDAR++: Accurate Depth for 3D Object Detection in Autonomous Driving. International Conference on Learning Representations 2020.
306	Disp R-CNN		code	57.98 %	79.61 %	47.09 %	0.387 s	GPU @ 2.5 Ghz (Python + C/C++)
J. Sun, L. Chen, Y. Xie, S. Zhang, Q. Jiang, X. Zhou and H. Bao: Disp R-CNN: Stereo 3D Object Detection via Shape Prior Guided Instance Disparity Estimation. CVPR 2020.
307	ZoomNet		code	54.91 %	72.94 %	44.14 %	0.3 s	1 core @ 2.5 Ghz (C/C++)
L. Z. Xu: ZoomNet: Part-Aware Adaptive Zooming Neural Network for 3D Object Detection. Proceedings of the AAAI Conference on Artificial Intelligence 2020.
308	VoxelJones		code	53.96 %	66.21 %	47.66 %	.18 s	1 core @ 2.5 Ghz (Python + C/C++)
M. Motro and J. Ghosh: Vehicular Multi-object Tracking with Persistent Detector Failures. arXiv preprint arXiv:1907.11306 2019.
309	TopNet-HighRes			53.05 %	67.84 %	46.99 %	101ms	NVIDIA GeForce 1080 Ti (tensorflow-gpu)
S. Wirges, T. Fischer, C. Stiller and J. Frias: Object Detection and Classification in Occupancy Grid Maps Using Deep Convolutional Networks. 2018 21st International Conference on Intelligent Transportation Systems (ITSC) 2018.
310	OC Stereo		code	51.47 %	68.89 %	42.97 %	0.35 s	1 core @ 2.5 Ghz (Python + C/C++)
A. Pon, J. Ku, C. Li and S. Waslander: Object-Centric Stereo Matching for 3D Object Detection. ICRA 2020.
311	YOLOStereo3D		code	50.28 %	76.10 %	36.86 %	0.1 s	GPU 1080Ti
Y. Liu, L. Wang and M. Liu: YOLOStereo3D: A Step Back to 2D for Efficient Stereo 3D Detection. 2021 International Conference on Robotics and Automation (ICRA) 2021.
312	SST [st]			47.07 %	71.08 %	41.90 %	1 s	1 core @ 2.5 Ghz (Python)
313	RT3DStereo			46.82 %	58.81 %	38.38 %	0.08 s	GPU @ 2.5 Ghz (C/C++)
H. Königshof, N. Salscheider and C. Stiller: Realtime 3D Object Detection for Automated Driving Using Stereo Vision and Semantic Information. Proc. IEEE Intl. Conf. Intelligent Transportation Systems 2019.
314	Pseudo-Lidar		code	45.00 %	67.30 %	38.40 %	0.4 s	GPU @ 2.5 Ghz (Python + C/C++)
Y. Wang, W. Chao, D. Garg, B. Hariharan, M. Campbell and K. Weinberger: Pseudo-LiDAR From Visual Depth Estimation: Bridging the Gap in 3D Object Detection for Autonomous Driving. The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2019.
315	BKDStereo3D		code	44.02 %	70.19 %	32.78 %	0.1 s	1 core @ 2.5 Ghz (Python)
ERROR: Wrong syntax in BIBTEX file.
316	RT3D			44.00 %	56.44 %	42.34 %	0.09 s	GPU @ 1.8Ghz
Y. Zeng, Y. Hu, S. Liu, J. Ye, Y. Han, X. Li and N. Sun: RT3D: Real-Time 3-D Vehicle Detection in LiDAR Point Cloud for Autonomous Driving. IEEE Robotics and Automation Letters 2018.
317	Stereo CenterNet			42.12 %	62.97 %	35.37 %	0.04 s	GPU @ 2.5 Ghz (Python)
Y. Shi, Y. Guo, Z. Mi and X. Li: Stereo CenterNet-based 3D object detection for autonomous driving. Neurocomputing 2022.
318	Stereo R-CNN		code	41.31 %	61.92 %	33.42 %	0.3 s	GPU @ 2.5 Ghz (Python)
P. Li, X. Chen and S. Shen: Stereo R-CNN based 3D Object Detection for Autonomous Driving. CVPR 2019.
319	BKDStereo3D w/o KD		code	40.69 %	67.38 %	29.98 %	0.1 s	1 core @ 2.5 Ghz (C/C++)
ERROR: Wrong syntax in BIBTEX file.
320	MonoTRKDv2			36.89 %	46.87 %	33.39 %	40 s	1 core @ 2.5 Ghz (Python)
321	DA3D+KM3D+v2-99			34.88 %	44.27 %	30.29 %	0.120s	GPU @ 2.5 Ghz (Python)
Y. Jia, J. Wang, H. Pan and W. Sun: Enhancing Monocular 3-D Object Detection Through Data Augmentation Strategies. IEEE Transactions on Instrumentation and Measurement 2024.
322	CIE + DM3D			33.13 %	46.17 %	28.80 %	0.1 s	1 core @ 2.5 Ghz (C/C++)
Ananimities: Consistency of Implicit and Explicit Features Matters for Monocular 3D Object Detection. arXiv preprint arXiv:2207.07933 2022.
323	StereoFENet			32.96 %	49.29 %	25.90 %	0.15 s	1 core @ 3.5 Ghz (Python)
W. Bao, B. Xu and Z. Chen: MonoFENet: Monocular 3D Object Detection with Feature Enhancement Networks. IEEE Transactions on Image Processing 2019.
324	MonoTAKD V2			32.31 %	43.83 %	28.48 %	0.1 s	1 core @ 2.5 Ghz (Python)
325	error			30.78 %	49.96 %	26.51 %	1 s	1 core @ 2.5 Ghz (Python)
326	monodetrnext-a			30.68 %	37.32 %	31.29 %	0.04 s	1 core @ 2.5 Ghz (C/C++)
327	Mobile Stereo R-CNN			28.78 %	44.51 %	22.30 %	1.8 s	NVIDIA Jetson TX2
M. Hussein, M. Khalil and B. Abdullah: 3D Object Detection using Mobile Stereo R- CNN on Nvidia Jetson TX2. International Conference on Advanced Engineering, Technology and Applications (ICAETA) 2021.
328	DA3D+KM3D		code	28.71 %	39.50 %	25.20 %	0.02 s	GPU @ 2.5 Ghz (Python)
Y. Jia, J. Wang, H. Pan and W. Sun: Enhancing Monocular 3-D Object Detection Through Data Augmentation Strategies. IEEE Transactions on Instrumentation and Measurement 2024.
329	CIE			28.50 %	41.41 %	23.88 %	0.1 s	1 core @ 2.5 Ghz (C/C++)
Anonymities: Consistency of Implicit and Explicit Features Matters for Monocular 3D Object Detection. arXiv preprint arXiv:2207.07933 2022.
330	monodetrnext-f			28.12 %	34.56 %	28.33 %	0.03 s	GPU @ 2.5 Ghz (Python)
331	MonoTAKD			27.76 %	38.75 %	24.14 %	0.1 s	1 core @ 2.5 Ghz (Python)
332	MonoLTKD			27.76 %	38.75 %	24.14 %	0.04 s	1 core @ 2.5 Ghz (C/C++)
333	MonoLTKD_V3			27.75 %	38.75 %	24.13 %	0.04 s	1 core @ 2.5 Ghz (Python)
ERROR: Wrong syntax in BIBTEX file.
334	DA3D			26.92 %	36.83 %	23.41 %	0.03 s	1 core @ 2.5 Ghz (Python)
Y. Jia, J. Wang, H. Pan and W. Sun: Enhancing Monocular 3-D Object Detection Through Data Augmentation Strategies. IEEE Transactions on Instrumentation and Measurement 2024.
335	MonoLiG		code	26.83 %	35.73 %	24.24 %	0.03 s	1 core @ 2.5 Ghz (C/C++)
A. Hekimoglu, M. Schmidt and A. Ramiro: Monocular 3D Object Detection with LiDAR Guided Semi Supervised Active Learning. 2023.
336	Sample		code	26.21 %	35.31 %	22.28 %	0.01 s	1 core @ 2.5 Ghz (C/C++)
337	MonoLSS			25.95 %	34.89 %	22.59 %	0.04 s	1 core @ 2.5 Ghz (Python)
Z. Li, J. Jia and Y. Shi: MonoLSS: Learnable Sample Selection For Monocular 3D Detection. International Conference on 3D Vision 2024.
338	CMKD		code	25.82 %	38.98 %	22.80 %	0.1 s	1 core @ 2.5 Ghz (C/C++)
Y. Hong, H. Dai and Y. Ding: Cross-Modality Knowledge Distillation Network for Monocular 3D Object Detection. ECCV 2022.
339	Occlude3D		code	25.41 %	33.08 %	20.75 %	0.01 s	1 core @ 2.5 Ghz (Python)
340	PS-SVDM			24.82 %	38.18 %	20.89 %	1 s	1 core @ 2.5 Ghz (Python)
Y. Shi: SVDM: Single-View Diffusion Model for Pseudo-Stereo 3D Object Detection. arXiv preprint arXiv:2307.02270 2023.
341	LPCG-Monoflex		code	24.81 %	35.96 %	21.86 %	0.03 s	1 core @ 2.5 Ghz (C/C++)
L. Peng, F. Liu, Z. Yu, S. Yan, D. Deng, Z. Yang, H. Liu and D. Cai: Lidar Point Cloud Guided Monocular 3D Object Detection. ECCV 2022.
342	Anonymous			24.66 %	34.65 %	20.77 %	0.1 s	1 core @ 2.5 Ghz (C/C++)
343	NeurOCS			24.49 %	37.27 %	20.89 %	0.1 s	GPU @ 2.5 Ghz (Python)
Z. Min, B. Zhuang, S. Schulter, B. Liu, E. Dunn and M. Chandraker: NeurOCS: Neural NOCS Supervision for Monocular 3D Object Localization. CVPR 2023.
344	Mix-Teaching		code	24.23 %	35.74 %	20.80 %	30 s	1 core @ 2.5 Ghz (C/C++)
L. Yang, X. Zhang, L. Wang, M. Zhu, C. Zhang and J. Li: Mix-Teaching: A Simple, Unified and Effective Semi-Supervised Learning Framework for Monocular 3D Object Detection. ArXiv 2022.
345	MonoAux-v2		code	24.15 %	34.14 %	20.84 %	0.04 s	GPU @ 2.5 Ghz (Python)
346	MonoSKD		code	24.08 %	37.12 %	20.37 %	0.04 s	1 core @ 2.5 Ghz (Python)
S. Wang and J. Zheng: MonoSKD: General Distillation Framework for Monocular 3D Object Detection via Spearman Correlation Coefficient. ECAI 2023.
347	MonoSample (DID-M3D)		code	23.94 %	37.64 %	20.46 %	0.2 s	1 core @ 2.5 Ghz (C/C++)
J. Qiao, B. Liu, J. Yang, B. Wang, S. Xiu, X. Du and X. Nie: MonoSample: Synthetic 3D Data Augmentation Method in Monocular 3D Object Detection. IEEE Robotics and Automation Letters 2024.
348	TBD			23.87 %	37.10 %	20.24 %	0.04 s	1 core @ 2.5 Ghz (C/C++)
349	PS-fld		code	23.76 %	32.64 %	20.64 %	0.25 s	1 core @ 2.5 Ghz (C/C++)
Y. Chen, H. Dai and Y. Ding: Pseudo-Stereo for Monocular 3D Object Detection in Autonomous Driving. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2022.
350	MSFENet		code	23.65 %	36.81 %	20.06 %	0.1 s	1 core @ 2.5 Ghz (Python)
351	SHUD			23.63 %	36.39 %	20.01 %	0.04 s	1 core @ 2.5 Ghz (Python)
352	ADD		code	23.58 %	35.20 %	20.08 %	0.1 s	1 core @ 2.5 Ghz (Python)
Z. Wu, Y. Wu, J. Pu, X. Li and X. Wang: Attention-based Depth Distillation with 3D-Aware Positional Encoding for Monocular 3D Object Detection. AAAI2023 .
353	MonoNeRD		code	23.46 %	31.13 %	20.97 %	na s	1 core @ 2.5 Ghz (Python)
J. Xu, L. Peng, H. Cheng, H. Li, W. Qian, K. Li, W. Wang and D. Cai: MonoNeRD: NeRF-like Representations for Monocular 3D Object Detection. ICCV 2023.
354	MonoDDE			23.46 %	33.58 %	20.37 %	0.04 s	1 core @ 2.5 Ghz (Python)
Z. Li, Z. Qu, Y. Zhou, J. Liu, H. Wang and L. Jiang: Diversity Matters: Fully Exploiting Depth Clues for Reliable Monocular 3D Object Detection. CVPR 2022.
355	DD3D		code	23.41 %	32.35 %	20.42 %	n/a s	1 core @ 2.5 Ghz (C/C++)
D. Park, R. Ambrus, V. Guizilini, J. Li and A. Gaidon: Is Pseudo-Lidar needed for Monocular 3D Object detection?. IEEE/CVF International Conference on Computer Vision (ICCV) .
356	MonoSGC			23.27 %	35.78 %	19.92 %	0.04 s	1 core @ 2.5 Ghz (C/C++)
357	FDGNet		code	23.27 %	36.25 %	19.56 %	0.1 s	1 core @ 2.5 Ghz (C/C++)
358	MonoUNI		code	23.05 %	33.28 %	19.39 %	0.04 s	1 core @ 2.5 Ghz (Python)
J. Jia, Z. Li and Y. Shi: MonoUNI: A Unified Vehicle and Infrastructure-side Monocular 3D Object Detection Network with Sufficient Depth Clues. Thirty-seventh Conference on Neural Information Processing Systems 2023.
359	MonoCD		code	22.81 %	33.41 %	19.57 %	n/a s	1 core @ 2.5 Ghz (Python)
L. Yan, P. Yan, S. Xiong, X. Xiang and Y. Tan: MonoCD: Monocular 3D Object Detection with Complementary Depths. CVPR 2024.
360	MonoFRD			22.77 %	29.65 %	20.41 %	0.01 s	1 core @ 2.5 Ghz (C/C++)
361	DID-M3D		code	22.76 %	32.95 %	19.83 %	0.04 s	1 core @ 2.5 Ghz (Python)
L. Peng, X. Wu, Z. Yang, H. Liu and D. Cai: DID-M3D: Decoupling Instance Depth for Monocular 3D Object Detection. ECCV 2022.
362	OPA-3D		code	22.53 %	33.54 %	19.22 %	0.04 s	1 core @ 3.5 Ghz (Python)
Y. Su, Y. Di, G. Zhai, F. Manhardt, J. Rambach, B. Busam, D. Stricker and F. Tombari: OPA-3D: Occlusion-Aware Pixel-Wise Aggregation for Monocular 3D Object Detection. IEEE Robotics and Automation Letters 2023.
363	MonoSTL			22.42 %	32.19 %	19.48 %	na s	1 core @ 2.5 Ghz (Python)
364	MonoCDiT			21.97 %	30.32 %	18.80 %	0.05 s	GPU @ >3.5 Ghz (Python)
365	BA2-Det+MonoFlex			21.54 %	31.61 %	18.35 %	0.03 s	1 core @ 2.5 Ghz (C/C++)
366	DCD		code	21.50 %	32.55 %	18.25 %	0.03 s	1 core @ 2.5 Ghz (C/C++)
Y. Li, Y. Chen, J. He and Z. Zhang: Densely Constrained Depth Estimator for Monocular 3D Object Detection. European Conference on Computer Vision 2022.
367	MonoDETR		code	21.45 %	32.20 %	18.68 %	0.04 s	1 core @ 2.5 Ghz (Python)
R. Zhang, H. Qiu, T. Wang, X. Xu, Z. Guo, Y. Qiao, P. Gao and H. Li: MonoDETR: Depth-aware Transformer for Monocular 3D Object Detection. arXiv preprint arXiv:2203.13310 2022.
368	SGM3D		code	21.37 %	31.49 %	18.43 %	0.03 s	1 core @ 2.5 Ghz (C/C++)
Z. Zhou, L. Du, X. Ye, Z. Zou, X. Tan, L. Zhang, X. Xue and J. Feng: SGM3D: Stereo Guided Monocular 3D Object Detection. RA-L 2022.
369	Cube R-CNN		code	21.20 %	31.70 %	18.43 %	0.05 s	GPU @ 2.5 Ghz (Python)
G. Brazil, A. Kumar, J. Straub, N. Ravi, J. Johnson and G. Gkioxari: Omni3D: A Large Benchmark and Model for 3D Object Detection in the Wild. CVPR 2023.
370	GUPNet		code	21.19 %	30.29 %	18.20 %	NA s	1 core @ 2.5 Ghz (Python + C/C++)
Y. Lu, X. Ma, L. Yang, T. Zhang, Y. Liu, Q. Chu, J. Yan and W. Ouyang: Geometry Uncertainty Projection Network for Monocular 3D Object Detection. arXiv preprint arXiv:2107.13774 2021.
371	MonoSIM_v2			21.19 %	30.36 %	18.45 %	0.03 s	1 core @ 2.5 Ghz (C/C++)
372	HomoLoss(monoflex)		code	20.68 %	29.60 %	17.81 %	0.04 s	1 core @ 2.5 Ghz (Python)
J. Gu, B. Wu, L. Fan, J. Huang, S. Cao, Z. Xiang and X. Hua: Homography Loss for Monocular 3D Object Detection. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2022.
373	DEVIANT		code	20.44 %	29.65 %	17.43 %	0.04 s	1 GPU (Python)
A. Kumar, G. Brazil, E. Corona, A. Parchami and X. Liu: DEVIANT: Depth EquiVarIAnt NeTwork for Monocular 3D Object Detection. European Conference on Computer Vision (ECCV) 2022.
374	MonoDTR			20.38 %	28.59 %	17.14 %	0.04 s	1 core @ 2.5 Ghz (C/C++)
K. Huang, T. Wu, H. Su and W. Hsu: MonoDTR: Monocular 3D Object Detection with Depth-Aware Transformer. CVPR 2022.
375	MDSNet			20.14 %	32.81 %	15.77 %	0.05 s	1 core @ 2.5 Ghz (Python)
Z. Xie, Y. Song, J. Wu, Z. Li, C. Song and Z. Xu: MDS-Net: Multi-Scale Depth Stratification 3D Object Detection from Monocular Images. Sensors 2022.
376	MonoSIM			20.09 %	28.68 %	18.28 %	0.16 s	1 core @ 2.5 Ghz (Python)
377	AutoShape		code	20.08 %	30.66 %	15.95 %	0.04 s	1 core @ 2.5 Ghz (C/C++)
Z. Liu, D. Zhou, F. Lu, J. Fang and L. Zhang: AutoShape: Real-Time Shape-Aware Monocular 3D Object Detection. Proceedings of the IEEE/CVF International Conference on Computer Vision 2021.
378	MonoFlex			19.75 %	28.23 %	16.89 %	0.03 s	GPU @ 2.5 Ghz (Python)
Y. Zhang, J. Lu and J. Zhou: Objects are Different: Flexible Monocular 3D Object Detection. CVPR 2021.
379	MonoEF			19.70 %	29.03 %	17.26 %	0.03 s	1 core @ 2.5 Ghz (Python)
Y. Zhou, Y. He, H. Zhu, C. Wang, H. Li and Q. Jiang: Monocular 3D Object Detection: An Extrinsic Parameter Free Approach. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2021.
380	MonOAPC			19.67 %	28.91 %	16.99 %	0035 s	1 core @ 2.5 Ghz (Python)
H. Yao, J. Chen, Z. Wang, X. Wang, P. Han, X. Chai and Y. Qiu: Occlusion-Aware Plane-Constraints for Monocular 3D Object Detection. IEEE Transactions on Intelligent Transportation Systems 2023.
381	MonoDSSMs-M			19.59 %	28.29 %	16.34 %	0.02 s	1 core @ 2.5 Ghz (Python + C/C++)
382	HomoLoss(imvoxelnet)		code	19.25 %	29.18 %	16.21 %	0.20 s	1 core @ 2.5 Ghz (Python)
J. Gu, B. Wu, L. Fan, J. Huang, S. Cao, Z. Xiang and X. Hua: Homogrpahy Loss for Monocular 3D Object Detection. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2022.
383	DFR-Net			19.17 %	28.17 %	14.84 %	0.18 s	1080 Ti (Pytorch)
Z. Zou, X. Ye, L. Du, X. Cheng, X. Tan, L. Zhang, J. Feng, X. Xue and E. Ding: The devil is in the task: Exploiting reciprocal appearance-localization features for monocular 3d object detection . ICCV 2021.
384	PS-SVDM			19.07 %	28.52 %	16.30 %	1 s	1 core @ 2.5 Ghz (Python)
Y. Shi: SVDM: Single-View Diffusion Model for Pseudo-Stereo 3D Object Detection. arXiv preprint arXiv:2307.02270 2023.
385	DLE		code	19.05 %	31.09 %	14.13 %	0.06 s	NVIDIA Tesla V100
C. Liu, S. Gu, L. Gool and R. Timofte: Deep Line Encoding for Monocular 3D Object Detection and Depth Prediction. Proceedings of the British Machine Vision Conference (BMVC) 2021.
386	PCT		code	19.03 %	29.65 %	15.92 %	0.045 s	1 core @ 2.5 Ghz (C/C++)
L. Wang, L. Zhang, Y. Zhu, Z. Zhang, T. He, M. Li and X. Xue: Progressive Coordinate Transforms for Monocular 3D Object Detection. NeurIPS 2021.
387	CaDDN		code	18.91 %	27.94 %	17.19 %	0.63 s	GPU @ 2.5 Ghz (Python)
C. Reading, A. Harakeh, J. Chae and S. Waslander: Categorical Depth Distribution Network for Monocular 3D Object Detection. CVPR 2021.
388	monodle		code	18.89 %	24.79 %	16.00 %	0.04 s	GPU @ 2.5 Ghz (Python)
X. Ma, Y. Zhang, D. Xu, D. Zhou, S. Yi, H. Li and W. Ouyang: Delving into Localization Errors for Monocular 3D Object Detection. CVPR 2021 .
389	Neighbor-Vote			18.65 %	27.39 %	16.54 %	0.1 s	GPU @ 2.5 Ghz (Python)
X. Chu, J. Deng, Y. Li, Z. Yuan, Y. Zhang, J. Ji and Y. Zhang: Neighbor-Vote: Improving Monocular 3D Object Detection through Neighbor Distance Voting. ACM MM 2021.
390	MonoRCNN++		code	18.62 %	27.20 %	15.69 %	0.07 s	GPU @ 2.5 Ghz (Python)
X. Shi, Z. Chen and T. Kim: Multivariate Probabilistic Monocular 3D Object Detection. WACV 2023.
391	GrooMeD-NMS		code	18.27 %	26.19 %	14.05 %	0.12 s	1 core @ 2.5 Ghz (Python)
A. Kumar, G. Brazil and X. Liu: GrooMeD-NMS: Grouped Mathematically Differentiable NMS for Monocular 3D Object Detection. CVPR 2021.
392	MonoRCNN		code	18.11 %	25.48 %	14.10 %	0.07 s	GPU @ 2.5 Ghz (Python)
X. Shi, Q. Ye, X. Chen, C. Chen, Z. Chen and T. Kim: Geometry-based Distance Decomposition for Monocular 3D Object Detection. ICCV 2021.
393	Ground-Aware		code	17.98 %	29.81 %	13.08 %	0.05 s	1 core @ 2.5 Ghz (C/C++)
Y. Liu, Y. Yuan and M. Liu: Ground-aware Monocular 3D Object Detection for Autonomous Driving. IEEE Robotics and Automation Letters 2021.
394	Aug3D-RPN			17.89 %	26.00 %	14.18 %	0.08 s	1 core @ 2.5 Ghz (C/C++)
C. He, J. Huang, X. Hua and L. Zhang: Aug3D-RPN: Improving Monocular 3D Object Detection by Synthetic Images with Virtual Depth. 2021.
395	DDMP-3D			17.89 %	28.08 %	13.44 %	0.18 s	1 core @ 2.5 Ghz (Python)
L. Wang, L. Du, X. Ye, Y. Fu, G. Guo, X. Xue, J. Feng and L. Zhang: Depth-conditioned Dynamic Message Propagation for Monocular 3D Object Detection. CVPR 2020.
396	IAFA			17.88 %	25.88 %	15.35 %	0.04 s	1 core @ 2.5 Ghz (C/C++)
D. Zhou, X. Song, Y. Dai, J. Yin, F. Lu, M. Liao, J. Fang and L. Zhang: IAFA: Instance-Aware Feature Aggregation for 3D Object Detection from a Single Image. Proceedings of the Asian Conference on Computer Vision 2020.
397	mdab			17.74 %	26.42 %	15.71 %	22 s	1 core @ 2.5 Ghz (C/C++)
398	FMF-occlusion-net			17.60 %	27.39 %	13.25 %	0.16 s	1 core @ 2.5 Ghz (Python + C/C++)
H. Liu, H. Liu, Y. Wang, F. Sun and W. Huang: Fine-grained Multi-level Fusion for Anti- occlusion Monocular 3D Object Detection. IEEE Transactions on Image Processing 2022.
399	RefinedMPL			17.60 %	28.08 %	13.95 %	0.15 s	GPU @ 2.5 Ghz (Python + C/C++)
J. Vianney, S. Aich and B. Liu: RefinedMPL: Refined Monocular PseudoLiDAR for 3D Object Detection in Autonomous Driving. arXiv preprint arXiv:1911.09712 2019.
400	Kinematic3D		code	17.52 %	26.69 %	13.10 %	0.12 s	1 core @ 1.5 Ghz (C/C++)
G. Brazil, G. Pons-Moll, X. Liu and B. Schiele: Kinematic 3D Object Detection in Monocular Video. ECCV 2020 .
401	MonoAuxNorm			17.38 %	23.43 %	14.74 %	0.02 s	GPU @ 2.5 Ghz (Python)
402	MonoRUn		code	17.34 %	27.94 %	15.24 %	0.07 s	GPU @ 2.5 Ghz (Python + C/C++)
H. Chen, Y. Huang, W. Tian, Z. Gao and L. Xiong: MonoRUn: Monocular 3D Object Detection by Reconstruction and Uncertainty Propagation. IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2021.
403	AM3D			17.32 %	25.03 %	14.91 %	0.4 s	GPU @ 2.5 Ghz (Python + C/C++)
X. Ma, Z. Wang, H. Li, P. Zhang, W. Ouyang and X. Fan: Accurate Monocular Object Detection via Color- Embedded 3D Reconstruction for Autonomous Driving. Proceedings of the IEEE international Conference on Computer Vision (ICCV) 2019.
404	YoloMono3D		code	17.15 %	26.79 %	12.56 %	0.05 s	GPU @ 2.5 Ghz (Python)
Y. Liu, L. Wang and L. Ming: YOLOStereo3D: A Step Back to 2D for Efficient Stereo 3D Detection. 2021 International Conference on Robotics and Automation (ICRA) 2021.
405	CMAN			17.04 %	25.89 %	12.88 %	0.15 s	1 core @ 2.5 Ghz (Python)
C. Yuanzhouhan Cao: CMAN: Leaning Global Structure Correlation for Monocular 3D Object Detection. IEEE Trans. Intell. Transport. Syst. 2022.
406	GAC3D			16.93 %	25.80 %	12.50 %	0.25 s	1 core @ 2.5 Ghz (Python)
M. Bui, D. Ngo, H. Pham and D. Nguyen: GAC3D: improving monocular 3D object detection with ground-guide model and adaptive convolution. 2021.
407	PatchNet		code	16.86 %	22.97 %	14.97 %	0.4 s	1 core @ 2.5 Ghz (C/C++)
X. Ma, S. Liu, Z. Xia, H. Zhang, X. Zeng and W. Ouyang: Rethinking Pseudo-LiDAR Representation. Proceedings of the European Conference on Computer Vision (ECCV) 2020.
408	PGD-FCOS3D		code	16.51 %	26.89 %	13.49 %	0.03 s	1 core @ 2.5 Ghz (C/C++)
T. Wang, X. Zhu, J. Pang and D. Lin: Probabilistic and Geometric Depth: Detecting Objects in Perspective. Conference on Robot Learning (CoRL) 2021.
409	ImVoxelNet		code	16.37 %	25.19 %	13.58 %	0.2 s	GPU @ 2.5 Ghz (Python)
D. Rukhovich, A. Vorontsova and A. Konushin: ImVoxelNet: Image to Voxels Projection for Monocular and Multi-View General-Purpose 3D Object Detection. arXiv preprint arXiv:2106.01178 2021.
410	KM3D		code	16.20 %	23.44 %	14.47 %	0.03 s	1 core @ 2.5 Ghz (Python)
P. Li: Monocular 3D Detection with Geometric Constraints Embedding and Semi-supervised Training. 2020.
411	D4LCN		code	16.02 %	22.51 %	12.55 %	0.2 s	GPU @ 2.5 Ghz (Python + C/C++)
M. Ding, Y. Huo, H. Yi, Z. Wang, J. Shi, Z. Lu and P. Luo: Learning Depth-Guided Convolutions for Monocular 3D Object Detection. CVPR 2020.
412	MonoAIU			15.68 %	23.01 %	12.87 %	0.03 s	GPU @ 2.5 Ghz (Python)
413	mdab			15.09 %	23.18 %	13.38 %	22 s	1 core @ 2.5 Ghz (Python)
414	MonoPair			14.83 %	19.28 %	12.89 %	0.06 s	GPU @ 2.5 Ghz (Python + C/C++)
Y. Chen, L. Tai, K. Sun and M. Li: MonoPair: Monocular 3D Object Detection Using Pairwise Spatial Relationships. The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2020.
415	Decoupled-3D			14.82 %	23.16 %	11.25 %	0.08 s	GPU @ 2.5 Ghz (C/C++)
Y. Cai, B. Li, Z. Jiao, H. Li, X. Zeng and X. Wang: Monocular 3D Object Detection with Decoupled Structured Polygon Estimation and Height-Guided Depth Estimation. AAAI 2020.
416	QD-3DT		code	14.71 %	20.16 %	12.76 %	0.03 s	GPU @ 2.5 Ghz (Python)
H. Hu, Y. Yang, T. Fischer, F. Yu, T. Darrell and M. Sun: Monocular Quasi-Dense 3D Object Tracking. ArXiv:2103.07351 2021.
417	SMOKE		code	14.49 %	20.83 %	12.75 %	0.03 s	GPU @ 2.5 Ghz (Python)
Z. Liu, Z. Wu and R. Tóth: SMOKE: Single-Stage Monocular 3D Object Detection via Keypoint Estimation. 2020.
418	RTM3D		code	14.20 %	19.17 %	11.99 %	0.05 s	GPU @ 1.0 Ghz (Python)
P. Li, H. Zhao, P. Liu and F. Cao: RTM3D: Real-time Monocular 3D Detection from Object Keypoints for Autonomous Driving. 2020.
419	Mono3D_PLiDAR		code	13.92 %	21.27 %	11.25 %	0.1 s	NVIDIA GeForce 1080 (pytorch)
X. Weng and K. Kitani: Monocular 3D Object Detection with Pseudo-LiDAR Point Cloud. arXiv:1903.09847 2019.
420	M3D-RPN		code	13.67 %	21.02 %	10.23 %	0.16 s	GPU @ 1.5 Ghz (Python)
G. Brazil and X. Liu: M3D-RPN: Monocular 3D Region Proposal Network for Object Detection . ICCV 2019 .
421	CSoR			13.07 %	18.67 %	10.34 %	3.5 s	4 cores @ >3.5 Ghz (Python + C/C++)
L. Plotkin: PyDriver: Entwicklung eines Frameworks für räumliche Detektion und Klassifikation von Objekten in Fahrzeugumgebung. 2015.
422	mdab			12.67 %	18.79 %	10.41 %	0.02 s	1 core @ 2.5 Ghz (Python)
423	MonoPSR		code	12.58 %	18.33 %	9.91 %	0.2 s	GPU @ 3.5 Ghz (Python)
J. Ku*, A. Pon* and S. Waslander: Monocular 3D Object Detection Leveraging Accurate Proposals and Shape Reconstruction. CVPR 2019.
424	Plane-Constraints		code	12.06 %	17.31 %	10.05 %	0.05 s	4 cores @ 3.0 Ghz (Python)
H. Yao, J. Chen, Z. Wang, X. Wang, X. Chai, Y. Qiu and P. Han: Vertex points are not enough: Monocular 3D object detection via intra-and inter-plane constraints. Neural Networks 2023.
425	MonoCInIS			11.64 %	22.28 %	9.95 %	0,13 s	GPU @ 2.5 Ghz (C/C++)
J. Heylen, M. De Wolf, B. Dawagne, M. Proesmans, L. Van Gool, W. Abbeloos, H. Abdelkawy and D. Reino: MonoCInIS: Camera Independent Monocular 3D Object Detection using Instance Segmentation. Proceedings of the IEEE/CVF International Conference on Computer Vision 2021.
426	SS3D			11.52 %	16.33 %	9.93 %	48 ms	Tesla V100 (Python)
E. Jörgensen, C. Zach and F. Kahl: Monocular 3D Object Detection and Box Fitting Trained End-to-End Using Intersection-over-Union Loss. CoRR 2019.
427	mdab			11.47 %	17.81 %	9.08 %	0.02 s	1 core @ 2.5 Ghz (Python)
428	MonoGRNet		code	11.17 %	18.19 %	8.73 %	0.04s	NVIDIA P40
Z. Qin, J. Wang and Y. Lu: MonoGRNet: A Geometric Reasoning Network for 3D Object Localization. The Thirty-Third AAAI Conference on Artificial Intelligence (AAAI-19) 2019.
429	MonoFENet			11.03 %	17.03 %	9.05 %	0.15 s	1 core @ 3.5 Ghz (Python)
W. Bao, B. Xu and Z. Chen: MonoFENet: Monocular 3D Object Detection with Feature Enhancement Networks. IEEE Transactions on Image Processing 2019.
430	MonoCInIS			10.96 %	20.42 %	9.23 %	0,14 s	GPU @ 2.5 Ghz (Python)
J. Heylen, M. De Wolf, B. Dawagne, M. Proesmans, L. Van Gool, W. Abbeloos, H. Abdelkawy and D. Reino: MonoCInIS: Camera Independent Monocular 3D Object Detection using Instance Segmentation. Proceedings of the IEEE/CVF International Conference on Computer Vision 2021.
431	A3DODWTDA (image)		code	8.66 %	10.37 %	7.06 %	0.8 s	GPU @ 3.0 Ghz (Python)
F. Gustafsson and E. Linder-Norén: Automotive 3D Object Detection Without Target Domain Annotations. 2018.
432	TLNet (Stereo)		code	7.69 %	13.71 %	6.73 %	0.1 s	1 core @ 2.5 Ghz (Python)
Z. Qin, J. Wang and Y. Lu: Triangulation Learning Network: from Monocular to Stereo 3D Object Detection. IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2019.
433	Shift R-CNN (mono)		code	6.82 %	11.84 %	5.27 %	0.25 s	GPU @ 1.5 Ghz (Python)
A. Naiden, V. Paunescu, G. Kim, B. Jeon and M. Leordeanu: Shift R-CNN: Deep Monocular 3D Object Detection With Closed-form Geometric Constraints. ICIP 2019.
434	SparVox3D			6.39 %	10.20 %	5.06 %	0.05 s	GPU @ 2.0 Ghz (Python)
E. Balatkan and F. Kıraç: Improving Regression Performance on Monocular 3D Object Detection Using Bin-Mixing and Sparse Voxel Data. 2021 6th International Conference on Computer Science and Engineering (UBMK) 2021.
435	GS3D			6.08 %	8.41 %	4.94 %	2 s	1 core @ 2.5 Ghz (C/C++)
B. Li, W. Ouyang, L. Sheng, X. Zeng and X. Wang: GS3D: An Efficient 3D Object Detection Framework for Autonomous Driving. IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2019.
436	MVRA + I-FRCNN+			5.84 %	9.05 %	4.50 %	0.18 s	GPU @ 2.5 Ghz (Python)
H. Choi, H. Kang and Y. Hyun: Multi-View Reprojection Architecture for Orientation Estimation. The IEEE International Conference on Computer Vision (ICCV) Workshops 2019.
437	WeakM3D		code	5.66 %	11.82 %	4.08 %	0.08 s	1 core @ 2.5 Ghz (C/C++)
L. Peng, S. Yan, B. Wu, Z. Yang, X. He and D. Cai: WeakM3D: Towards Weakly Supervised Monocular 3D Object Detection. ICLR 2022.
438	ROI-10D			4.91 %	9.78 %	3.74 %	0.2 s	GPU @ 3.5 Ghz (Python)
F. Manhardt, W. Kehl and A. Gaidon: ROI-10D: Monocular Lifting of 2D Detection to 6D Pose and Metric Shape. Computer Vision and Pattern Recognition (CVPR) 2019.
439	3D-GCK			4.57 %	5.79 %	3.64 %	24 ms	Tesla V100
N. Gählert, J. Wan, N. Jourdan, J. Finkbeiner, U. Franke and J. Denzler: Single-Shot 3D Detection of Vehicles from Monocular RGB Images via Geometrically Constrained Keypoints in Real-Time. 2020 IEEE Intelligent Vehicles Symposium (IV) 2020.
440	FQNet			3.23 %	5.40 %	2.46 %	0.5 s	1 core @ 2.5 Ghz (Python)
L. Liu, J. Lu, C. Xu, Q. Tian and J. Zhou: Deep Fitting Degree Scoring Network for Monocular 3D Object Detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition 2019.
441	3D-SSMFCNN		code	2.63 %	3.20 %	2.40 %	0.1 s	GPU @ 1.5 Ghz (C/C++)
L. Novak: Vehicle Detection and Pose Estimation for Autonomous Driving. 2017.
442	VeloFCN			0.14 %	0.02 %	0.21 %	1 s	GPU @ 2.5 Ghz (Python + C/C++)
B. Li, T. Zhang and T. Xia: Vehicle Detection from 3D Lidar Using Fully Convolutional Network. RSS 2016 .
443	f3sd		code	0.01 %	0.00 %	0.01 %	1.67 s	1 core @ 2.5 Ghz (C/C++)
444	multi-task CNN			0.00 %	0.00 %	0.00 %	25.1 ms	GPU @ 2.0 Ghz (Python)
M. Oeljeklaus, F. Hoffmann and T. Bertram: A Fast Multi-Task CNN for Spatial Understanding of Traffic Scenes. IEEE Intelligent Transportation Systems Conference 2018.
445	mBoW			0.00 %	0.00 %	0.00 %	10 s	1 core @ 2.5 Ghz (C/C++)
J. Behley, V. Steinhage and A. Cremers: Laser-based Segment Classification Using a Mixture of Bag-of-Words. Proc. of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) 2013.

Pedestrian