Deep Learning for 3D Point Cloud Understanding: A Survey

Our survey paper[ArXiv]

@article{lu2020deep,
  title={Deep Learning for 3D Point Cloud Understanding: A Survey},
  author={Lu, Haoming and Shi, Humphrey},
  journal={arXiv preprint arXiv:2009.08920},
  year={2020}
}

Content

• Datasets
• Metrics
• Papers
  • 3D Object Classification
    • Projection-based classification
    • Point-based classification
  • 3D Segmentation
    • Semantic segmentation
    • Instance segmentation
    • Joint training
  • 3D Object Detection
    • Projection-based detection
    • Point-based detection
    • Multi-view fusion
  • 3D Object Tracking
  • 3D Scene Flow Estimation
  • 3D Point Registration and Matching
  • Point Cloud Augmentation and Completion
    • Discriminative methods
    • Generative methods

Datasets

• ShapeNet
• ModelNet
• S3DIS
• Semantic3D
• ScanNet
• KITTI
• 3DMatch
• nuScenes
• Lyft Level 5
• Waymo Open Dataset

Metrics

Name	Formula	Explanation
Accuracy		Accuracy indicates how many predictions are correct over all predictions. ``Overall accuracy (OA)" indicates the accuracy on the entire dataset.
mACC		The mean of accuracy on different categories, useful when the categories are imbalanced.
Precision		The ratio of correct predictions over all predictions.
Recall		The ratio of correct predictions over positive samples in the ground truth.
F1 Score		The harmonic mean of precision and recall.
IoU		Intersection over Union (of class/instance $i$). The intersection and union are calculated between the prediction and the ground truth.
mIoU		The mean of IoU on all classes/instances.
MOTA		Multi-object tracking accuracy (MOTA) synthesizes 3 error sources: false positives, missed targets and identity switches, and the number of ground truth (as TP+FN) is used for normalization.
MOTP		Multi-object tracking precision (MOTP) indicates the precision of localization. denotes the number of matches at time t, and denotes the error of the i-th pair at time t.
EPE		End point error (EPE) is used in scene flow estimation, also referred as EPE2D/EPE3D for 2D/3D data respectively. denotes the predicted scene flow vector while denotes the ground truth.

Papers (up to ECCV 2020)

3D Object Classification

Projection-based classification

• Su, Hang, et al. "Multi-view convolutional neural networks for 3d shape recognition." Proceedings of the IEEE international conference on computer vision. 2015. [paper]

• Feng, Yifan, et al. "Gvcnn: Group-view convolutional neural networks for 3d shape recognition." Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2018. [paper]

• Yu, Tan, Jingjing Meng, and Junsong Yuan. "Multi-view harmonized bilinear network for 3d object recognition." Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2018. [paper]

• Yang, Ze, and Liwei Wang. "Learning relationships for multi-view 3D object recognition." Proceedings of the IEEE International Conference on Computer Vision. 2019. [paper]

• Maturana, Daniel, and Sebastian Scherer. "Voxnet: A 3d convolutional neural network for real-time object recognition." 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). IEEE, 2015. [paper]

• Wu, Zhirong, et al. "3d shapenets: A deep representation for volumetric shapes." Proceedings of the IEEE conference on computer vision and pattern recognition. 2015. [paper]

• Riegler, Gernot, Ali Osman Ulusoy, and Andreas Geiger. "Octnet: Learning deep 3d representations at high resolutions." Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2017. [paper]

• Prokudin, Sergey, Christoph Lassner, and Javier Romero. "Efficient learning on point clouds with basis point sets." Proceedings of the IEEE International Conference on Computer Vision. 2019. [paper]

Point-based classification

• Qi, Charles R., et al. "Pointnet: Deep learning on point sets for 3d classification and segmentation." Proceedings of the IEEE conference on computer vision and pattern recognition. 2017. [paper]

• Qi, Charles Ruizhongtai, et al. "Pointnet++: Deep hierarchical feature learning on point sets in a metric space." Advances in neural information processing systems. 2017. [paper]

• Zhao, Hengshuang, et al. "PointWeb: Enhancing local neighborhood features for point cloud processing." Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2019. [paper]

• Duan, Yueqi, et al. "Structural relational reasoning of point clouds." Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2019. [paper]

• Komarichev, Artem, Zichun Zhong, and Jing Hua. "A-CNN: Annularly convolutional neural networks on point clouds." Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2019. [paper]

• Liu, Yongcheng, et al. "Relation-shape convolutional neural network for point cloud analysis." Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2019. [paper]

• Wu, Wenxuan, Zhongang Qi, and Li Fuxin. "Pointconv: Deep convolutional networks on 3d point clouds." Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2019. [paper]

• Hermosilla, Pedro, et al. "Monte carlo convolution for learning on non-uniformly sampled point clouds." ACM Transactions on Graphics (TOG) 37.6 (2018): 1-12. [paper]

• Lan, Shiyi, et al. "Modeling local geometric structure of 3D point clouds using Geo-CNN." Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2019. [paper]

• Rao, Yongming, Jiwen Lu, and Jie Zhou. "Spherical fractal convolutional neural networks for point cloud recognition." Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2019. [paper]

• Simonovsky, Martin, and Nikos Komodakis. "Dynamic edge-conditioned filters in convolutional neural networks on graphs." Proceedings of the IEEE conference on computer vision and pattern recognition. 2017. [paper]

• Wang, Yue, et al. "Dynamic graph cnn for learning on point clouds." Acm Transactions On Graphics (tog) 38.5 (2019): 1-12. [paper]

• Hassani, Kaveh, and Mike Haley. "Unsupervised multi-task feature learning on point clouds." Proceedings of the IEEE International Conference on Computer Vision. 2019. [paper]

• Chen, Chao, et al. "Clusternet: Deep hierarchical cluster network with rigorously rotation-invariant representation for point cloud analysis." Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2019. [paper]

• Klokov, Roman, and Victor Lempitsky. "Escape from cells: Deep kd-networks for the recognition of 3d point cloud models." Proceedings of the IEEE International Conference on Computer Vision. 2017. [paper]

• Zeng, Wei, and Theo Gevers. "3DContextNet: Kd tree guided hierarchical learning of point clouds using local and global contextual cues." Proceedings of the European Conference on Computer Vision (ECCV). 2018. [paper]

• Wu, Pengxiang, et al. "Point cloud processing via recurrent set encoding." Proceedings of the AAAI Conference on Artificial Intelligence. Vol. 33. 2019. [paper]

• Li, Jiaxin, Ben M. Chen, and Gim Hee Lee. "So-net: Self-organizing network for point cloud analysis." Proceedings of the IEEE conference on computer vision and pattern recognition. 2018. [paper]

3D Segmentation

Semantic segmentation

• Huang, Jing, and Suya You. "Point cloud labeling using 3d convolutional neural network." 2016 23rd International Conference on Pattern Recognition (ICPR). IEEE, 2016. [paper]

• Dai, Angela, et al. "Scancomplete: Large-scale scene completion and semantic segmentation for 3d scans." Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2018. [paper]

• Meng, Hsien-Yu, et al. "Vv-net: Voxel vae net with group convolutions for point cloud segmentation." Proceedings of the IEEE International Conference on Computer Vision. 2019. [paper]

• Lawin, Felix Järemo, et al. "Deep projective 3D semantic segmentation." International Conference on Computer Analysis of Images and Patterns. Springer, Cham, 2017. [paper]

• Zhang, Yang, et al. "PolarNet: An Improved Grid Representation for Online LiDAR Point Clouds Semantic Segmentation." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2020. [paper]

• Dai, Angela, and Matthias Nießner. "3dmv: Joint 3d-multi-view prediction for 3d semantic scene segmentation." Proceedings of the European Conference on Computer Vision (ECCV). 2018. [paper]

• Jaritz, Maximilian, Jiayuan Gu, and Hao Su. "Multi-view pointnet for 3d scene understanding." Proceedings of the IEEE International Conference on Computer Vision Workshops. 2019. [paper]

• Engelmann, Francis, et al. "Know what your neighbors do: 3D semantic segmentation of point clouds." Proceedings of the European Conference on Computer Vision (ECCV). 2018. [paper]

• Wang, Shenlong, et al. "Deep parametric continuous convolutional neural networks." Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2018. [paper]

• Liu, Zhijian, et al. "Point-Voxel CNN for efficient 3D deep learning." Advances in Neural Information Processing Systems. 2019. [paper]

• Hua, Binh-Son, Minh-Khoi Tran, and Sai-Kit Yeung. "Pointwise convolutional neural networks." Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2018. [paper]

• Landrieu, Loic, and Martin Simonovsky. "Large-scale point cloud semantic segmentation with superpoint graphs." Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2018. [paper]

• Landrieu, Loic, and Mohamed Boussaha. "Point cloud oversegmentation with graph-structured deep metric learning." Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2019. [paper]

• Wang, Lei, et al. "Graph attention convolution for point cloud semantic segmentation." Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2019. [paper]

• Tatarchenko, Maxim, et al. "Tangent convolutions for dense prediction in 3d." Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2018. [paper]

• Hu, Qingyong, et al. "RandLA-Net: Efficient semantic segmentation of large-scale point clouds." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2020. [paper]

• Xu, Xun, and Gim Hee Lee. "Weakly Supervised Semantic Point Cloud Segmentation: Towards 10x Fewer Labels." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2020. [paper]

• Wei, Jiacheng, et al. "Multi-Path Region Mining For Weakly Supervised 3D Semantic Segmentation on Point Clouds." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2020. [paper]

Instance segmentation

• Hou, Ji, Angela Dai, and Matthias Nießner. "3d-sis: 3d semantic instance segmentation of rgb-d scans." Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2019. [paper]

• Yi, Li, et al. "Gspn: Generative shape proposal network for 3d instance segmentation in point cloud." Proceedings of the IEEE conference on computer vision and pattern recognition. 2019. [paper]

• Yang, Ze, and Liwei Wang. "Learning relationships for multi-view 3D object recognition." Proceedings of the IEEE International Conference on Computer Vision. 2019. [paper]

• Zhang, Feihu, et al. "Instance segmentation of lidar point clouds." ICRA, Cited by 4.1 (2020). [paper]

• Wang, Weiyue, et al. "Sgpn: Similarity group proposal network for 3d point cloud instance segmentation." Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2018. [paper]

• Lahoud, Jean, et al. "3d instance segmentation via multi-task metric learning." Proceedings of the IEEE International Conference on Computer Vision. 2019. [paper]

• Zhang, Biao, and Peter Wonka. "Point cloud instance segmentation using probabilistic embeddings." arXiv preprint arXiv:1912.00145 (2019). [paper]

• Wu, Bichen, et al. "Squeezeseg: Convolutional neural nets with recurrent crf for real-time road-object segmentation from 3d lidar point cloud." 2018 IEEE International Conference on Robotics and Automation (ICRA). IEEE, 2018. [paper]

• Wu, Bichen, et al. "Squeezesegv2: Improved model structure and unsupervised domain adaptation for road-object segmentation from a lidar point cloud." 2019 International Conference on Robotics and Automation (ICRA). IEEE, 2019. [paper]

• Lyu, Yecheng, Xinming Huang, and Ziming Zhang. "Learning to Segment 3D Point Clouds in 2D Image Space." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2020. [paper]

• Jiang, Li, et al. "PointGroup: Dual-Set Point Grouping for 3D Instance Segmentation." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2020. [paper]

Joint training

• Hassani, Kaveh, and Mike Haley. "Unsupervised multi-task feature learning on point clouds." Proceedings of the IEEE International Conference on Computer Vision. 2019. [paper]
• Pham, Quang-Hieu, et al. "JSIS3D: joint semantic-instance segmentation of 3d point clouds with multi-task pointwise networks and multi-value conditional random fields." Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2019. [paper]
• Wang, Xinlong, et al. "Associatively segmenting instances and semantics in point clouds." Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2019. [paper]

3D Object Detection

Projection-based detection

• Zhou, Yin, and Oncel Tuzel. "Voxelnet: End-to-end learning for point cloud based 3d object detection." Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2018. [paper]
• Yan, Yan, Yuxing Mao, and Bo Li. "Second: Sparsely embedded convolutional detection." Sensors 18.10 (2018): 3337. [paper]
• Lang, Alex H., et al. "Pointpillars: Fast encoders for object detection from point clouds." Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2019. [paper]
• Wang, Yue, et al. "Pillar-based Object Detection for Autonomous Driving." Proceedings of the European Conference on Computer Vision (ECCV). (2020). [paper]
• He, Chenhang, et al. "Structure Aware Single-stage 3D Object Detection from Point Cloud." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2020. [paper]

Point-based detection

• Yang, Zetong, et al. "Std: Sparse-to-dense 3d object detector for point cloud." Proceedings of the IEEE International Conference on Computer Vision. 2019. [paper]
• Shi, Shaoshuai, Xiaogang Wang, and Hongsheng Li. "Pointrcnn: 3d object proposal generation and detection from point cloud." Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2019. [paper]
• Qi, Charles R., et al. "Deep hough voting for 3d object detection in point clouds." Proceedings of the IEEE International Conference on Computer Vision. 2019. [paper]
• Qi, Charles R., et al. "Imvotenet: Boosting 3d object detection in point clouds with image votes." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2020. [paper]
• Du, Liang, et al. "Associate-3Ddet: Perceptual-to-Conceptual Association for 3D Point Cloud Object Detection." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2020. [paper]
• Yang, Zetong, et al. "3dssd: Point-based 3d single stage object detector." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2020. [paper]
• Zarzar, Jesus, Silvio Giancola, and Bernard Ghanem. "PointRGCN: Graph convolution networks for 3D vehicles detection refinement." arXiv preprint arXiv:1911.12236 (2019). [paper]
• Chen, Jintai, et al. "A Hierarchical Graph Network for 3D Object Detection on Point Clouds." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2020. [paper]
• Shi, Weijing, and Raj Rajkumar. "Point-gnn: Graph neural network for 3d object detection in a point cloud." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2020. [paper]

Multi-view fusion

• Chen, Xiaozhi, et al. "Multi-view 3d object detection network for autonomous driving." Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2017. [paper]

• Liang, Ming, et al. "Deep continuous fusion for multi-sensor 3d object detection." Proceedings of the European Conference on Computer Vision (ECCV). 2018. [paper]

• Lu, Haihua, et al. "SCANet: Spatial-channel attention network for 3D object detection." ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 2019. [paper]

• Zeng, Yiming, et al. "Rt3d: Real-time 3-d vehicle detection in lidar point cloud for autonomous driving." IEEE Robotics and Automation Letters 3.4 (2018): 3434-3440. [paper]

• Qi, Charles R., et al. "Frustum pointnets for 3d object detection from rgb-d data." Proceedings of the IEEE conference on computer vision and pattern recognition. 2018. [paper]

• Gupta, Ayush. "Deep Sensor Fusion for 3D Bounding Box Estimation and Recognition of Objects." [paper]

3D Object Tracking

• Giancola, Silvio, Jesus Zarzar, and Bernard Ghanem. "Leveraging shape completion for 3d siamese tracking." Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2019. [paper]
• Zarzar, Jesus, Silvio Giancola, and Bernard Ghanem. "PointRGCN: Graph convolution networks for 3D vehicles detection refinement." arXiv preprint arXiv:1911.12236 (2019). [paper]
• Chiu, Hsu-kuang, et al. "Probabilistic 3d multi-object tracking for autonomous driving." arXiv preprint arXiv:2001.05673 (2020). [paper]
• Qi, Haozhe, et al. "P2B: Point-to-Box Network for 3D Object Tracking in Point Clouds." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2020. [paper]

3D Scene Flow Estimation

• Liu, Xingyu, Charles R. Qi, and Leonidas J. Guibas. "Flownet3d: Learning scene flow in 3d point clouds." Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2019. [paper]
• Wang, Zirui, et al. "FlowNet3D++: Geometric losses for deep scene flow estimation." The IEEE Winter Conference on Applications of Computer Vision. 2020. [paper]
• Gu, Xiuye, et al. "Hplflownet: Hierarchical permutohedral lattice flownet for scene flow estimation on large-scale point clouds." Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2019. [paper]
• Liu, Xingyu, Mengyuan Yan, and Jeannette Bohg. "Meteornet: Deep learning on dynamic 3d point cloud sequences." Proceedings of the IEEE International Conference on Computer Vision. 2019. [paper]
• Fan, Hehe, and Yi Yang. "PointRNN: Point recurrent neural network for moving point cloud processing." arXiv preprint arXiv:1910.08287 (2019). [paper]

3D Point Registration and Matching

• Lu, Weixin, et al. "Deepvcp: An end-to-end deep neural network for point cloud registration." Proceedings of the IEEE International Conference on Computer Vision. 2019. [paper]

• Gojcic, Zan, et al. "The perfect match: 3d point cloud matching with smoothed densities." Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2019. [paper]

• Gojcic, Zan, et al. "Learning multiview 3D point cloud registration." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2020. [paper]

• Yew, Zi Jian, and Gim Hee Lee. "RPM-Net: Robust Point Matching using Learned Features." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2020. [paper]

Point Cloud Augmentation and Completion

Discriminative methods

• Rakotosaona, Marie‐Julie, et al. "Pointcleannet: Learning to denoise and remove outliers from dense point clouds." Computer Graphics Forum. Vol. 39. No. 1. 2020. [paper]

• Guerrero, Paul, et al. "Pcpnet learning local shape properties from raw point clouds." Computer Graphics Forum. Vol. 37. No. 2. 2018. [paper]

• Hermosilla, Pedro, Tobias Ritschel, and Timo Ropinski. "Total Denoising: Unsupervised learning of 3D point cloud cleaning." Proceedings of the IEEE International Conference on Computer Vision. 2019. [paper]

• Nezhadarya, Ehsan, et al. "Adaptive Hierarchical Down-Sampling for Point Cloud Classification." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2020. [paper]

• Lang, Itai, Asaf Manor, and Shai Avidan. "SampleNet: Differentiable Point Cloud Sampling." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2020. [paper]

Generative methods

• Xiang, Chong, Charles R. Qi, and Bo Li. "Generating 3d adversarial point clouds." Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2019. [paper]

• Shu, Dong Wook, Sung Woo Park, and Junseok Kwon. "3d point cloud generative adversarial network based on tree structured graph convolutions." Proceedings of the IEEE International Conference on Computer Vision. 2019. [paper]

• Zhou, Hang, et al. "DUP-Net: Denoiser and upsampler network for 3D adversarial point clouds defense." Proceedings of the IEEE International Conference on Computer Vision. 2019. [paper]

• Yu, Lequan, et al. "Pu-net: Point cloud upsampling network." Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2018. [paper]

• Yifan, Wang, et al. "Patch-based progressive 3d point set upsampling." Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2019. [paper]

• Hui, Le, et al. "Progressive Point Cloud Deconvolution Generation Network." Proceedings of the European Conference on Computer Vision (ECCV). (2020). [paper]

• Yuan, Wentao, et al. "Pcn: Point completion network." 2018 International Conference on 3D Vision (3DV). IEEE, 2018. [paper]

• Wang, Xiaogang, Marcelo H. Ang Jr, and Gim Hee Lee. "Cascaded Refinement Network for Point Cloud Completion." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2020. [paper]

• Huang, Zitian, et al. "PF-Net: Point Fractal Network for 3D Point Cloud Completion." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2020. [paper]

• Xie, Haozhe, et al. "GRNet: Gridding Residual Network for Dense Point Cloud Completion." Proceedings of the European Conference on Computer Vision (ECCV). (2020). [paper]

• Lan, Ziquan, Zi Jian Yew, and Gim Hee Lee. "Robust Point Cloud Based Reconstruction of Large-Scale Outdoor Scenes." Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2019. [paper]

• Li, Ruihui, et al. "Pu-gan: a point cloud upsampling adversarial network." Proceedings of the IEEE International Conference on Computer Vision. 2019. [paper]

• Sarmad, Muhammad, Hyunjoo Jenny Lee, and Young Min Kim. "Rl-gan-net: A reinforcement learning agent controlled gan network for real-time point cloud shape completion." Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2019. [paper]

• Wu, Rundi, et al. "Multimodal Shape Completion via Conditional Generative Adversarial Networks." Proceedings of the European Conference on Computer Vision (ECCV). (2020). [paper]