{"id":18005591,"url":"https://github.com/kuixu/3d-deep-learning","last_synced_at":"2026-01-28T16:33:24.352Z","repository":{"id":89422123,"uuid":"68037987","full_name":"kuixu/3d-deep-learning","owner":"kuixu","description":"3D Deep Learning works","archived":false,"fork":false,"pushed_at":"2019-05-10T03:52:06.000Z","size":17,"stargazers_count":142,"open_issues_count":0,"forks_count":36,"subscribers_count":9,"default_branch":"master","last_synced_at":"2025-05-28T17:55:34.947Z","etag":null,"topics":["3d","3d-shapes","deep-learning","volumetric-data"],"latest_commit_sha":null,"homepage":null,"language":null,"has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/kuixu.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2016-09-12T18:53:33.000Z","updated_at":"2025-05-22T00:14:07.000Z","dependencies_parsed_at":null,"dependency_job_id":"1679bef2-350a-4d34-b1a4-448bdf111580","html_url":"https://github.com/kuixu/3d-deep-learning","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/kuixu/3d-deep-learning","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kuixu%2F3d-deep-learning","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kuixu%2F3d-deep-learning/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kuixu%2F3d-deep-learning/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kuixu%2F3d-deep-learning/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/kuixu","download_url":"https://codeload.github.com/kuixu/3d-deep-learning/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kuixu%2F3d-deep-learning/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":28847017,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-01-28T15:15:36.453Z","status":"ssl_error","status_checked_at":"2026-01-28T15:15:13.020Z","response_time":57,"last_error":"SSL_read: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["3d","3d-shapes","deep-learning","volumetric-data"],"created_at":"2024-10-30T00:20:44.000Z","updated_at":"2026-01-28T16:33:24.331Z","avatar_url":"https://github.com/kuixu.png","language":null,"funding_links":[],"categories":[],"sub_categories":[],"readme":"# 3d-deep-learning\n3D Deep Learning works\n\n\n## Tasks\n\n\n### 3D Representation\n\n#### Spherical CNNs\n  - Taco S. Cohen, Spherical CNNs, ICLR 2018 Best paper \\[[paper](https://openreview.net/forum?id=Hkbd5xZRb)\\] \n  - Learning SO\\(3\\) Equivariant Representations with Spherical CNNs \\[[paper](https://arxiv.org/pdf/1711.06721v2.pdf)] [[code](https://github.com/daniilidis-group/spherical-cnn)]\n  - Deep Learning Advances on Different 3D Data\nRepresentations: A Survey  \\[[paper](https://arxiv.org/pdf/1808.01462.pdf)\\] \n\n\n### 3D Classification\n\n#### Datasets\n\n  - [ModelNet10/40](http://3dshapenets.cs.princeton.edu)\n\n#### Networks\n\n  - 3D CNN\n      - [3D-DenseNet](https://github.com/barrykui/3ddensenet.torch)\n      - Voxnet: A 3d convolutional neural network for real-time object recognition, IROS 2015.  \\[[code](https://github.com/dimatura/voxnet)\\] \\[[paper](http://arxiv.org/abs/1505.00880)\\]\n      - [3D-NIN, network in network]\n      - VRN Ensemble, Generative and discriminative voxel modeling with convolutional neural networks, arxiv \\[[paper](https://arxiv.org/pdf/1608.04236.pdf)] \\[[code](https://github.com/ajbrock/Generative-and-Discriminative-Voxel-Modeling)\\]\n        - Voxception-Resnet Blocks\n  - 2D CNN\n        - MVCNN, Learned-Miller.Multi- view convolutional neural networks for 3d shape recognition, ICCV2015 \\[[project](http://vis-www.cs.umass.edu/mvcnn/)\\] \\[[code](https://github.com/suhangpro/mvcnn)\\] \\[[paper](http://arxiv.org/abs/1505.00880)\\]\\[[data](http://maxwell.cs.umass.edu/mvcnn-data/)\\] \\[[video](http://vis-www.cs.umass.edu/mvcnn/docs/1694_video.mp4)\\]\n  - Point\n      - PointNet \\[[project](http://stanford.edu/~rqi/pointnet/)]\\[[paper](http://arxiv.org/abs/1612.00593)]\\[[code](https://github.com/charlesq34/pointnet)]\\[[video](https://www.youtube.com/watch?v=Cge-hot0Oc0)][[slides](http://stanford.edu/~rqi/pointnet/docs/cvpr17_pointnet_slides.pdf)]\n        - global pooling\n        - T-net\n      - PointNet++ \\[[paper](https://arxiv.org/pdf/1706.02413.pdf)\\] \\[[code](https://github.com/charlesq34/pointnet2)] \n        - sampling \u0026 grouping to learning local feature for fine-gaint objects\n        - two PointNet\n  - Graph/tree-based \n      - Kd-Net, scape from cells: Deep kd- networks for the recognition of 3d point cloud models, arxiv2017 \\[[paper](http://arxiv.org/abs/1704.01222)\\]\n        - kd-tree\n      - Octnet: Learning deep 3d representations at high resolutions, CVPR2017 \n        - octree\n      - O-cnn: Octree-based convolutional neural networks for 3d shape analysis, TOG2017\n        - octree\n      - SO-Net: Self-Organizing Network for Point Cloud Analysis, CVPR2018 \\[[paper](https://arxiv.org/abs/1803.04249)\\]  \\[[code](https://github.com/lijx10/SO-Net)\\]\n        - point-to-node kNN search Self-Organizing Map \\(SOM\\)  \n      - KCNet, Mining Point Cloud Local Structures by Kernel Correlation and Graph Pooling, CVPR2018   \\[[project](http://vis-www.cs.umass.edu/mvcnn/)\\] \\[[code](https://github.com/suhangpro/mvcnn)\\] \\[[paper](http://arxiv.org/abs/1505.00880)\\]\\[[data](http://maxwell.cs.umass.edu/mvcnn-data/)\\] \\[[video](http://vis-www.cs.umass.edu/mvcnn/docs/1694_video.mp4)\\]\n        - Kernel Correlation\n        - Graph Pooling\n      - \n\n### 3D Segmentation\n\n#### Datasets\n\n  - [HVSMR](http://segchd.csail.mit.edu/data.html)\n  - [BRATS Data](https://sites.google.com/site/braintumorsegmentation/home/brats2015)\n  - [ShapeNet]()\n\n#### Networks\n\n  - HeartSeg, 3D-FC-Densenet, Automatic 3D Cardiovascular MR Segmentation with \nDensely-Connected Volumetric ConvNets - MICCAI 2017 - [[code](https://github.com/yulequan/HeartSeg)]\n  - 3D-Unet \\[[paper](http://lmb.informatik.uni-freiburg.de/Publications/2016/CABR16/cicek16miccai.pdf)]\n  - ClusterNet: 3D Instance Segmentation in RGB-D Images \\[[paper](https://arxiv.org/pdf/1807.08894.pdf)\\]\n  - PointNet \\[[project](http://stanford.edu/~rqi/pointnet/)]\\[[paper](http://arxiv.org/abs/1612.00593)]\\[[code](https://github.com/charlesq34/pointnet)]\\[[video](https://www.youtube.com/watch?v=Cge-hot0Oc0)][[slides](http://stanford.edu/~rqi/pointnet/docs/cvpr17_pointnet_slides.pdf)]\n  - PointNet++ \\[[paper](https://arxiv.org/pdf/1706.02413.pdf)\\] \\[[code](https://github.com/charlesq34/pointnet2)] \n  - KCNet, Mining Point Cloud Local Structures by Kernel Correlation and Graph Pooling, CVPR2018   \\[[project](http://vis-www.cs.umass.edu/mvcnn/)\\] \\[[code](https://github.com/suhangpro/mvcnn)\\] \\[[paper](http://arxiv.org/abs/1505.00880)\\]\\[[data](http://maxwell.cs.umass.edu/mvcnn-data/)\\] \\[[video](http://vis-www.cs.umass.edu/mvcnn/docs/1694_video.mp4)\\]\n  - SO-Net: Self-Organizing Network for Point Cloud Analysis, CVPR2018 \\[[paper](https://arxiv.org/abs/1803.04249)\\]  \\[[code](https://github.com/lijx10/SO-Net)\\]\n  - 3D Shape Segmentation with Projective Convolutional Networks. CVPR2017. [`Project`](http://people.cs.umass.edu/~kalo/papers/shapepfcn/) [`Poster`](http://people.cs.umass.edu/~kalo/papers/shapepfcn/ShapePFCN_poster.pdf) [`Presentation`](http://people.cs.umass.edu/~kalo/papers/shapepfcn/ShapePFCN_poster.pdf) \n  - nnU-Net: Breaking the Spell on Successful Medical Image Segmentation \\[[paper](https://arxiv.org/pdf/1904.08128.pdf)\\] \\[[code](https://github.com/MIC-DKFZ/nnunet)] \n\n### 3D Object Detection\n\n#### Datasets\n\nData types: RGBD, Flow, Laser\n  - [KITTI](http://www.cvlibs.net/datasets/kitti/eval_object.php?obj_benchmark=3d)\n  - [KITTI Object Visualization Tool](https://github.com/barrykui/kitti_object_vis)\n\n#### Networks  \n\n  - MV3D, Multi-View 3D Object Detection Network for Autonomous Driving \\[[paper](https://arxiv.org/pdf/1611.07759)\\] [[code](https://github.com/bostondiditeam/MV3D)]\n  - Avod, Joint 3D Proposal Generation and Object Detection from View Aggregation \\[[paper](https://arxiv.org/abs/1712.02294)\\] [[code](https://github.com/kujason/avod)]\n  - F-PointNet, Frustum PointNets for 3D Object Detection from RGB-D Data \\[[paper](https://arxiv.org/abs/1711.08488)\\] \\[[code](https://github.com/charlesq34/frustum-pointnets)\\]\n  - VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection \\[[paper](https://arxiv.org/abs/1711.06396)\\]\n  - PIXOR: Real-time 3D Object Detection from Point Clouds - CVPR 2018 -  \\[[paper](http://openaccess.thecvf.com/content_cvpr_2018/papers/Yang_PIXOR_Real-Time_3D_CVPR_2018_paper.pdf)\\] \\[[code](https://github.com/charlesq34/frustum-pointnets)\\]\n  - 3D Object Proposals using Stereo Imagery for Accurate Object Class Detection \\[[paper](https://arxiv.org/abs/1608.07711)\\]\n  - 3D Bounding Box Estimation Using Deep Learning and Geometry \\[[paper](https://arxiv.org/abs/1612.00496)\\]  \\[[code](https://github.com/smallcorgi/3D-Deepbox)\\]\n  - [Learning 3D Object Orientations From Synthetic Images](http://cs231n.stanford.edu/reports/rqi_final_report.pdf)\n\n### 3D Reconstruction \u0026 Generation\n\n#### Datasets\n\nData types: RGBD, Flow, Laser\n  - ShapeNet\n\n#### Networks  \n\n  - SO-Net: Self-Organizing Network for Point Cloud Analysis, CVPR2018 \\[[paper](https://arxiv.org/abs/1803.04249)\\]  \\[[code](https://github.com/lijx10/SO-Net)\\]\n  - 3D-GAN  \\[[paper](https://arxiv.org/abs/1612.00496)\\]  \\[[code](https://github.com/zck119/3dgan-release)\\]\n  - Generating 3D Adversarial Point Clouds \\[[paper](https://arxiv.org/pdf/1809.07016.pdf)\\] \n\n### 3D Human Pose Estimation\n\n#### Datasets\n\nData types: RGBD, Flow, Laser\n  - ShapeNet\n\n#### Networks  \n\n  - Synthetic Occlusion Data Augmentation -2018 ECCV PoseTrack Challenge - \\[[paper](https://arxiv.org/abs/1809.04987)\\] \\[[code](https://github.com/isarandi/synthetic-occlusion)\\]\n  - Towards 3D Human Pose Estimation in the Wild: a Weakly-supervised Approach - ICCV 2017  - \\[[paper](https://arxiv.org/abs/1809.04987)\\] \\[[code](https://github.com/xingyizhou/pose-hg-3d)\\] \\[[code-pytorch](https://github.com/xingyizhou/Pytorch-pose-hg-3d)\n  - 3D human pose estimation from depth maps using a deep combination of poses \\[[paper](https://arxiv.org/pdf/1807.05389.pdf)\\] \n\n\n## CVPR2016 Tutorial: 3D Deep Learning with Marvin\n  - [CVPR2016 Tutorial: 3D Deep Learning with Marvin](http://vision.princeton.edu/event/cvpr16/3DDeepLearning/)\n  - [3D Shape Retrieval](https://shapenet.cs.stanford.edu/shrec16/)\n  - [C3D](https://github.com/facebook/C3D), [website](http://www.cs.dartmouth.edu/~dutran/c3d/)\n  - [Video Caffe(C3D)] [[code](https://github.com/chuckcho/video-caffe)]\n  - [DeepMedic, Brain Lesion Segmentation] [[code(https://github.com/Kamnitsask/deepmedic)]\n  - [3D Keypoint Detection and Feature Description](http://staffhome.ecm.uwa.edu.au/~00051632/page100.html)\n\n## Codes and libs for 3D\n  - [util3d](https://github.com/fyu/util3d)\n  - [spectral-lib](https://github.com/mbhenaff/spectral-lib)\n  - [3D-Caffe](https://github.com/yulequan/3D-Caffe#installation)\n  - [3D-ResNets-PyTorch](https://github.com/kenshohara/3D-ResNets-PyTorch)\n\n\n## DL on Medical Image\n  - [Antibody-supervised deep learning for quantification of tumor-infiltrating immune cells in hematoxylin and eosin stained breast cancer samples](https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5027738/)\n\n## More 3D Papers\n\nsee [ [3D-Machine-Learning](https://github.com/timzhang642/3D-Machine-Learning)]\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fkuixu%2F3d-deep-learning","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fkuixu%2F3d-deep-learning","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fkuixu%2F3d-deep-learning/lists"}