Deep learning in 3D point cloud analysis: Registration, Object Detection and Segmentation.

A survey on Point Cloud based papers

Registration

• Discriminative Optimization: Theory and Applications to Point Cloud Registration, 2017 [Paper]

• 3D Point Cloud Registration for Localization using a Deep Neural Network Auto-Encoder, 2017. [Paper], [Code]

• Colored Point Cloud Registration Revisited, 2017. [Paper]

• Using 2 point+normal sets for fast registration of point clouds with small overlap, 2017. [Paper]

• Density Adaptive Point Set Registration, 2018. [Paper][Code]

• Learning and Matching Multi-View Descriptors for Registration of Point Clouds, 2018. [Paper]

• 3DFeat-Net: Weakly Supervised Local 3D Features for Point Cloud Registration.[Paper],[Code_TensorFlow]

• Inverse Composition Discriminative Optimization for Point Cloud Registration, 2018.[Paper]

• Efficient Global Point Cloud Registration by Matching Rotation Invariant Features Through Translation Search, 2018.[Paper]

• HGMR: Hierarchical Gaussian Mixtures for Adaptive 3D Registration, 2018.[Paper]

• Robust Generalized Point Cloud Registration Using Hybrid Mixture Model, 2018.[Paper]

• A General Framework for Flexible Multi-Cue Photometric Point Cloud Registration, 2018.[Paper]

• PointNetLK: Point Cloud Registration using PointNet, 2019. [Paper], [Code_Pytorch]

• SDRSAC: Semidefinite-Based Randomized Approach for Robust Point Cloud Registration without Correspondences, 2019.[Paper], [Code_Matlab]

• FilterReg: Robust and Efficient Probabilistic Point-Set Registration using Gaussian Filter and Twist Parameterization, 2019[Paper],[Code]

• PointNetLK: Robust & Efficient Point Cloud Registration using PointNet, 2019.[Paper], [Code_Pytorch]

• Learning multiview 3D point cloud registration, 2020.[Paper], [Code_Pytorch]

• Feature-metric Registration: A Fast Semi-supervised Approach for Robust Point Cloud Registration without Correspondences., 2020.[Paper], [Code_Pytorch]

Object Detection

• Vote3Deep: Fast object detection in 3D point clouds using efficient convolutional neural networks, 2017.[Paper], [Code]

• Deep learning of directional truncated signed distance function for robust 3D object recognition, 2017.[Paper].

• Analyzing the quality of matched 3D point clouds of objects, 2017.[Paper].

• PIXOR: Real-time 3D Object Detection from Point Clouds, 2018.[Paper], [Code_Pytorch]

• VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection, 2018.[Paper], [Code_Tensorflow]⭐

• Deep Continuous Fusion for Multi-Sensor 3D Object Detection, 2018.[Paper].

• YOLO3D: End-to-end real-time 3D Oriented Object Bounding Box Detection from LiDAR Point Cloud, 2018.[Paper]

• Joint 3D Proposal Generation and Object Detection from View Aggregation, 2018.[Paper].

• A 3D Convolutional Neural Network Towards Real-Time Amodal 3D Object Detection, 2018.[Paper].

• Complex-YOLO: Real-time 3D Object Detection on Point Clouds, 2018.[Paper], [Code_Pytorch]⭐.:cupcake:

• RoarNet: A Robust 3D Object Detection based on RegiOn Approximation Refinement, 2018.[Paper].

• Pseudo-LiDAR from Visual Depth Estimation: Bridging the Gap in 3D Object Detection for Autonomous Driving, 2019.[Paper], [Code]

• PointRCNN: 3D Object Proposal Generation and Detection from Point Cloud, 2019.[Paper], [Code_Pytorch].:cupcake:

• PointPillars: Fast Encoders for Object Detection from Point Clouds, 2019.[Paper], [Code_Pytorch].:cupcake:

• Deep Hough Voting for 3D Object Detection in Point Clouds, 2019.[Paper], [Code_Pytorch]

• MVX-Net: Multimodal VoxelNet for 3D Object Detection, 2019.[Paper].

• FVNet: 3D Front-View Proposal Generation for Real-Time Object Detection from Point Clouds, 2019[Paper], [Code]

• Complexer-YOLO: Real-Time 3D Object Detection and Tracking on Semantic Point Clouds, 2019[Paper], [Code_Pytorch]⭐.

• TANet: Robust 3D Object Detection from Point Clouds with Triple Attention, 2020.[Paper], [Code].

• MLCVNet: Multi-Level Context VoteNet for 3D Object Detection., 2020.[Paper], [Code].

• ImVoteNet: Boosting 3D Object Detection in Point Clouds with Image Votes, 2020.[Paper].

Deep Learning for 3D Point Clouds: A Survey, 2020.[Paper].

Solving occlusion probloems

• ScanComplete: Large-Scale Scene Completion and Semantic Segmentation for 3D Scans, 2018.[Paper], [Code] [taking an incomplete 3D scan of a scene as input and predicting a complete 3D model along with per-voxel semantic labels]
• ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes, 2017.[Paper], [Code_Pytorch]

Segmentation

• Unstructured point cloud semantic labeling using deep segmentation networks,2017.[Paper], [Code_Pytorch]
• Weakly Supervised Semantic Point Cloud Segmentation: Towards 10× Fewer Labels, 2020.[Paper], [Code]⭐
• Just Go with the Flow: Self-Supervised Scene Flow Estimation, 2020.[Paper], [Code]

Data Annotation

• Point Cloud Annotation Methods for 3D Deep Learning, 2019.[Paper], [Code_Pytorch]
• PointAtMe: Efficient 3D Point Cloud Labeling in Virtual Reality, 2020.[Paper], [Code]⭐⭐(Virtual Reality)
• SUSTech POINTS: A Portable 3D Point Cloud Interactive Annotation Platform System, 2020.[Paper], [Code]
• Multi-Label Point Cloud Annotation by Selection of Sparse Control Points, 2017.[Paper], [Code]⭐(ROS-Based)
• Leveraging Pre-Trained 3D Object Detection Models For Fast Ground Truth Generation, 2018.[Paper].:cupcake:
• , 2019.[Paper], [Code_Pytorch] , 2019.[Paper], [Code_Pytorch] , 2020.[Paper], [Code]