Awesome Point Cloud Learning

A curated list of papers & resources linked to deep learning on point sets.

• PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation[https://arxiv.org/abs/1612.00593] [CVPR2017]

  • [tensorflow][https://github.com/charlesq34/pointnet]

  • [pytorch][https://github.com/fxia22/pointnet.pytorch]

  • [pytorch][https://github.com/erikwijmans/Pointnet2_PyTorch]

• PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space[https://arxiv.org/abs/1706.02413] [NIPS2017]

  • [tensorflow][https://github.com/charlesq34/pointnet2]

  • [tensorflow][https://github.com/LinZhuoChen/pointnet2.multigpu]

  • [pytorch][https://github.com/erikwijmans/Pointnet2_PyTorch]

  • [pytorch][https://github.com/eriche2016/pointnet2.pytorch]

• KCNet: Mining Point Cloud Local Structures by Kernel Correlation and Graph Pooling[https://arxiv.org/abs/1712.06760] [CVPR2018]

  • [caffe][http://www.merl.com/research/?research=license-request&sw=KCNet]

  • [pytorch][https://github.com/ftdlyc/KCNet_Pytorch]

• Pointwise Convolutional Neural Networks[https://arxiv.org/abs/1712.05245] [CVPR2018]

  • [tensorflow][https://github.com/scenenn/pointwise]

• SO-Net: Self-Organizing Network for Point Cloud Analysis[https://arxiv.org/abs/1803.04249] [CVPR2018]

  • [pytorch][https://github.com/lijx10/SO-Net]

• Escape from Cells: Deep Kd-Networks for the Recognition of 3D Point Cloud Models[https://arxiv.org/abs/1704.01222] [ICCV2017]

  • [pytorch][https://github.com/fxia22/kdnet.pytorch]

• Recurrent Slice Networks for 3D Segmentation of Point Clouds[https://arxiv.org/abs/1802.04402] [CVPR2018]

  • [pytorch][https://github.com/qianguih/RSNet]

• SPLATNet: Sparse Lattice Networks for Point Cloud Processing[https://arxiv.org/abs/1802.08275] [CVPR2018]

  • [caffe][https://github.com/NVlabs/splatnet]

  • [pytorch][https://github.com/ftdlyc/splatnet_pytorch]

• Large-scale Point Cloud Semantic Segmentation with Superpoint Graphs[http://arxiv.org/abs/1711.09869] [CVPR2018]

  • [pytorch][https://github.com/loicland/superpoint_graph]

• Dynamic Graph CNN for Learning on Point Clouds[https://github.com/WangYueFt/dgcnn] [arxiv2018]

  • [tensorflow][https://github.com/WangYueFt/dgcnn]

• Local Spectral Graph Convolution for Point Set Feature Learning[https://arxiv.org/abs/1803.05827] [ECCV2018]

  • [tensorflow][https://github.com/fate3439/LocalSpecGCN]

• SpiderCNN: Deep Learning on Point Sets with Parameterized Convolutional Filters[https://arxiv.org/abs/1803.11527] [ECCV2018]

  • [tensorflow][https://github.com/xyf513/SpiderCNN]

• Point Convolutional Neural Networks by Extension Operators[https://arxiv.org/abs/1803.10091] [SIGGRAPH 2018]

  • [tensorflow][https://github.com/matanatz/pcnn]

• PointCNN: Convolution On X-Transformed Points[https://arxiv.org/abs/1801.07791] [NeurIPS 2018]

  • [tensorflow][https://github.com/yangyanli/PointCNN]

  • [mxnet][https://github.com/chinakook/PointCNN.MX]

  • [pytorch][https://github.com/hxdengBerkeley/PointCNN.Pytorch]

• PointSIFT: A SIFT-like Network Module for 3D Point Cloud Semantic Segmentation[https://arxiv.org/abs/1807.00652] [arxiv2018]

  • [tensorflow][https://github.com/MVIG-SJTU/pointSIFT]

  • [pytorch][https://github.com/Tommymhz/PointNet.PointNet2.PointSIFT.Pytorch]

• Relation-Shape Convolutional Neural Network for Point Cloud Analysis[https://arxiv.org/pdf/1904.07601.pdf] [CVPR2019]

  • [tensorflow][https://github.com/Yochengliu/Relation-Shape-CNN]

• Octree guided CNN with Spherical Kernels for 3D PointClouds[https://arxiv.org/abs/1903.00343] [CVPR2019]

  • [tensorflow][https://github.com/DylanWusee/pointconv]

• Modeling Local Geometric Structure of 3D Point Clouds using Geo-CNN[https://arxiv.org/abs/1811.07782] [CVPR2019]

• A-CNN: Annularly Convolutional Neural Networks on Point Clouds[https://arxiv.org/abs/1904.08017] [CVPR2019]

• 3D Point-Capsule Networks[https://arxiv.org/abs/1812.10775] [CVPR2019]

• Associatively Segmenting Instances and Semantics in Point Clouds[https://arxiv.org/abs/1902.09852] [CVPR2019]

  • [tensorflow][https://github.com/WXinlong/ASIS]