Minkowski Engine is an auto-diff neural network library for high-dimensional sparse tensors

[ICLR'23 Spotlight🔥] The first successful BERT/MAE-style pretraining on any convolutional network; Pytorch impl. of "Designing BERT for Convolutional Networks: Sparse and Hierarchical Masked Modeling"

Caffe for Sparse and Low-rank Deep Neural Networks

Focal Sparse Convolutional Networks for 3D Object Detection (CVPR 2022, Oral)

[NeurIPS 2022, T-PAMI 2023] Efficient Spatially Sparse Inference for Conditional GANs and Diffusion Models

ISBNet: a 3D Point Cloud Instance Segmentation Network with Instance-aware Sampling and Box-aware Dynamic Convolution (CVPR 2023)

[ECCV 2024] 3D Small Object Detection with Dynamic Spatial Pruning

Unofficial PyTorch implementation of the paper: "CenterNet3D: An Anchor free Object Detector for Autonomous Driving"

[IROS 2020] Indoor Scene Recognition in 3D

[CVPR24] MaGGIe: Mask Guided Gradual Human Instance Matting

Neural Medial Axis Approximation of Point Clouds for 3D Tree Skeletonization

Dynamic Frame Interpolation in Wavelet Domain (TIP 2023)

Open Source Project for 3D Semantic Segmentation

[WACV'25] Official implementation of "PK-YOLO: Pretrained Knowledge Guided YOLO for Brain Tumor Detection in Multiplane MRI Slices".

An implementation of Sparse Layers in TensorFlow 2. x.

Sparse ConvLSTM for Point Cloud Semantic Segmentation

A fast MATLAB toolbox for N-dimensional sparse arrays.

This repository is a Pytorch porting of the Escoin-caffe Sparse Convolution implementation.