MvDeCor: Multi-view Dense Correspondence Learning for Fine-Grained 3D Segmentation
Authors: 
Gopal Sharma, Kangxue Yin, Subhransu Maji, Evangelos Kalogerakis, Or Litany, and Sanja FidlerAuthors Info & Claims
Gopal Sharma, Kangxue Yin, Subhransu Maji, Evangelos Kalogerakis, Or Litany, and Sanja FidlerAuthors Info & ClaimsOctober 2022
Pages 550 - 567
Abstract
We propose to utilize self-supervised techniques in the 2D domain for fine-grained 3D shape segmentation tasks. This is inspired by the observation that view-based surface representations are more effective at modeling high-resolution surface details and texture than their 3D counterparts based on point clouds or voxel occupancy. Specifically, given a 3D shape, we render it from multiple views, and set up a dense correspondence learning task within the contrastive learning framework. As a result, the learned 2D representations are view-invariant and geometrically consistent, leading to better generalization when trained on a limited number of labeled shapes than alternatives based on self-supervision in 2D or 3D alone. Experiments on textured (RenderPeople) and untextured (PartNet) 3D datasets show that our method outperforms state-of-the-art alternatives in fine-grained part segmentation. The improvements over baselines are greater when only a sparse set of views is available for training or when shapes are textured, indicating that MvDeCor benefits from both 2D processing and 3D geometric reasoning. Project page: https://nv-tlabs.github.io/MvDeCor/.
References
[1]
Renderpeople. https://renderpeople.com/
[2]
Achlioptas, P., Diamanti, O., Mitliagkas, I., Guibas, L.J.: Learning representations and generative models for 3D point clouds. In: International Conference on Machine Learning (2018)
[3]
Alliegro, A., Boscaini, D., Tommasi, T.: Joint supervised and self-supervised learning for 3D real world challenges. In: 2020 25th International Conference on Pattern Recognition (ICPR), pp. 6718–6725. IEEE Computer Society (2021)
[4]
Chen, L.C., Zhu, Y., Papandreou, G., Schroff, F., Adam, H.: Encoder-decoder with atrous separable convolution for semantic image segmentation. In: ECCV (2018)
[5]
Chen, T., Kornblith, S., Norouzi, M., Hinton, G.: A simple framework for contrastive learning of visual representations. In: International Conference on Machine Learning, pp. 1597–1607 (2020)
[6]
Chen, Z., Yin, K., Fisher, M., Chaudhuri, S., Zhang, H.: BAE-NET: branched autoencoder for shape co-segmentation. In: International Conference on Computer Vision (ICCV), pp. 8490–8499 (2019)
[7]
Choy, C., Gwak, J., Savarese, S.: 4D spatio-temporal ConvNets: minkowski convolutional neural networks. In: Computer Vision and Pattern Recognition (CVPR), pp. 3075–3084 (2019)
[8]
Choy, C.B., Gwak, J., Savarese, S., Chandraker, M.: Universal correspondence network. In: Advances in Neural Information Processing Systems, vol. 30 (2016)
[9]
Gadelha M et al. Vedaldi A, Bischof H, Brox T, Frahm J-M, et al. Label-efficient learning on point clouds using approximate convex decompositions Computer Vision – ECCV 2020 2020 Cham Springer 473-491
[10]
Gadelha, M., Wang, R., Maji, S.: Multiresolution tree networks for 3D point cloud processing. In: ECCV (2018)
[11]
Genova, K., et al.: Learning 3D semantic segmentation with only 2D image supervision. In: International Conference on 3D Vision (3DV), pp. 361–372. IEEE (2021)
[12]
Ginzburg D and Raviv D Vedaldi A, Bischof H, Brox T, and Frahm J-M Cyclic functional mapping: self-supervised correspondence between non-isometric deformable shapes Computer Vision – ECCV 2020 2020 Cham Springer 36-52
[13]
Goyal, A., Law, H., Liu, B., Newell, A., Deng, J.: Revisiting point cloud shape classification with a simple and effective baseline. In: International Conference on Machine Learning (2021)
[14]
Grill, J.B., et al.: Bootstrap your own latent - a new approach to self-supervised learning. In: Advances in Neural Information Processing Systems, vol. 33 (2020)
[15]
Groueix, T., Fisher, M., Kim, V.G., Russell, B., Aubry, M.: AtlasNet: a papier-Mâché approach to learning 3D surface generation. In: Computer Vision and Pattern Recognition (CVPR) (2018)
[16]
Halimi, O., Litany, O., Rodola, E., Bronstein, A.M., Kimmel, R.: Unsupervised learning of dense shape correspondence. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4370–4379 (2019)
[17]
Hamdi, A., Giancola, S., Ghanem, B.: MVTN: multi-view transformation network for 3D shape recognition. In: Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), pp. 1–11 (2021)
[18]
Hassani, K., Haley, M.: Unsupervised multi-task feature learning on point clouds. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 8160–8171 (2019)
[19]
He, K., Fan, H., Wu, Y., Xie, S., Girshick, R.: Momentum contrast for unsupervised visual representation learning. In: 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 9726–9735 (2020).
[20]
Hou, J., Graham, B., Nießner, M., Xie, S.: Exploring data-efficient 3D scene understanding with contrastive scene contexts. In: Conference on Computer Vision and Pattern Recognition (CVPR), pp. 15587–15597 (2021)
[21]
Hou, J., Xie, S., Graham, B., Dai, A., Nießner, M.: Pri3d: can 3D priors help 2D representation learning? In: 2021 IEEE/CVF International Conference on Computer Vision (ICCV), pp. 5673–5682 (2021).
[22]
Huang H, Kalogerakis E, Chaudhuri S, Ceylan D, Kim VG, and Yumer E Learning local shape descriptors from part correspondences with multiview convolutional networks ACM Trans. Graph. 2018 37 1 1-14
[23]
Kalogerakis, E., Averkiou, M., Maji, S., Chaudhuri, S.: 3D shape segmentation with projective convolutional networks. In: Proceedings of CVPR (2017)
[24]
Kawana, Y., Mukuta, Y., Harada, T.: Neural star domain as primitive representation. In: Proceedings of the 34th International Conference on Neural Information Processing Systems, NIPS 2020. Curran Associates Inc., Red Hook (2020)
[25]
Kundu A et al. Vedaldi A, Bischof H, Brox T, Frahm J-M, et al. Virtual multi-view fusion for 3D semantic segmentation Computer Vision – ECCV 2020 2020 Cham Springer 518-535
[26]
Lien, J.M., Amato, N.M.: Approximate convex decomposition of polyhedra. In: ACM Symposium on Solid and Physical Modeling (2007)
[27]
Luo, W., Schwing, A.G., Urtasun, R.: Efficient deep learning for stereo matching. In: Computer Vision and Pattern Recognition (CVPR), pp. 5695–5703 (2016)
[28]
Mo, K., et al.: Partnet: a large-scale benchmark for fine-grained and hierarchical part-level 3D object understanding. In: Computer Vision and Pattern Recognition (CVPR) (2019)
[29]
Oord, A.V.D., Li, Y., Vinyals, O.: Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748 (2018)
[30]
Qi, C.R., Su, H., Mo, K., Guibas, L.J.: PointNet: deep learning on point sets for 3D classification and segmentation. In: Proceedings of CVPR (2017)
[31]
Sarlin, P.E., DeTone, D., Malisiewicz, T., Rabinovich, A.: SuperGlue: learning feature matching with graph neural networks. In: CVPR (2020)
[32]
Sauder, J., Sievers, B.: Self-supervised deep learning on point clouds by reconstructing space. In: Advances in Neural Information Processing Systems, pp. 12942–12952 (2019)
[33]
Sharma, G., et al.: PriFit: learning to fit primitives improves few shot point cloud segmentation. In: Computer Graphics Forum (2022).
[34]
Su, H., Maji, S., Kalogerakis, E., Learned-Miller, E.G.: Multi-view convolutional neural networks for 3D shape recognition. In: Proceedings of ICCV (2015)
[35]
Su, J.C., Gadelha, M., Wang, R., Maji, S.: A deeper look at 3D shape classifiers. In: European Conference on Computer Vision Workshops (ECCV) (2018)
[36]
Tulsiani, S., Su, H., Guibas, L.J., Efros, A.A., Malik, J.: Learning shape abstractions by assembling volumetric primitives. In: Computer Vision and Pattern Regognition (CVPR) (2017)
[37]
Wang, L., Li, X., Fang, Y.: Few-shot learning of part-specific probability space for 3D shape segmentation. In: Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4504–4513 (2020)
[38]
Wang, P.S., Yang, Y.Q., Zou, Q.F., Wu, Z., Liu, Y., Tong, X.: Unsupervised 3D learning for shape analysis via multiresolution instance discrimination (2021)
[39]
Wang, X., Zhang, R., Shen, C., Kong, T., Li, L.: Dense contrastive learning for self-supervised visual pre-training. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2021)
[40]
Wu, Z., Xiong, Y., Yu, S.X., Lin, D.: Unsupervised feature learning via non-parametric instance discrimination. In: Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3733–3742 (2018)
[41]
Xie S, Gu J, Guo D, Qi CR, Guibas L, and Litany O Vedaldi A, Bischof H, Brox T, and Frahm J-M PointContrast: unsupervised pre-training for 3D point cloud understanding Computer Vision – ECCV 2020 2020 Cham Springer 574-591
[42]
Yang, Y., Feng, C., Shen, Y., Tian, D.: FoldingNet: point cloud auto-encoder via deep grid deformation. In: Computer Vision and Pattern Recognition (CVPR), pp. 206–215 (2018)
[43]
Yi L et al. A scalable active framework for region annotation in 3D shape collections ACM Trans. Graph. 2016 35 6 1-12
[44]
Zhang, Z., Girdhar, R., Joulin, A., Misra, I.: Self-supervised pretraining of 3D features on any point-cloud. In: International Conference on Computer Vision (ICCV), pp. 10252–10263 (2021)
[45]
Zhi, S., Laidlow, T., Leutenegger, S., Davison, A.J.: In-place scene labelling and understanding with implicit scene representation. In: International Conference on Computer Vision (ICCV), pp. 15838–15847 (2021)
Index Terms
- MvDeCor: Multi-view Dense Correspondence Learning for Fine-Grained 3D Segmentation
Index terms have been assigned to the content through auto-classification.
Recommendations
Leveraging Fine-Grained Labels to Regularize Fine-Grained Visual Classification
ICCMS '19: Proceedings of the 11th International Conference on Computer Modeling and SimulationFine-grained visual categorization (FGVC) is challenging mainly due to the large intra-class confusion and small inter-class variance in terms of shape, pose, and appearance. We propose the concept of fine-grained label and that any given label can be ...
S3DS: Self-supervised Learning of 3D Skeletons from Single View Images
MM '23: Proceedings of the 31st ACM International Conference on Multimedia3D skeleton is an inherent structure of objects and is often used for shape analysis. However, most supervised deep learning methods, which directly obtain 3D skeletons from 2D images, are constrained by skeleton data preparation. In this paper, we ...
Deep, dense and accurate 3D face correspondence for generating population specific deformable models
A Deep Network trained on synthetic 3D data to detect facial landmarks is proposed.The landmarks are used to establish region based 3D face dense correspondence.Correspondence is established across identities and facial expressions.A Region based 3D ...
Comments
Information & Contributors
Information
Published In
Oct 2022
805 pages
ISBN:978-3-031-20085-4
DOI:10.1007/978-3-031-20086-1
© The Author(s), under exclusive license to Springer Nature Switzerland AG 2022.
Publisher
Springer-Verlag
Berlin, Heidelberg
Publication History
Published: 23 October 2022
Qualifiers
- Article
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 0Total Downloads
- Downloads (Last 12 months)0
- Downloads (Last 6 weeks)0
Other Metrics
Citations
View Options
View options
Get Access
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in