CVPR 2020 3D点云 文章汇总

一、点云文章资源

近年来，对于点云处理的研究越来越火热。Github上面有一个工程，汇总了从2017年以来各大会议上点云论文，awesome-point-cloud-analysis ,但尚未包括刚刚release的CVPR2020中的点云论文。

本文主要整理CVPR2020中的点云相关论文，总共70多篇，供大家查阅，后期还会持续更新文章分类和解读。

欢迎来到点云世界。

二、CVPR2020 点云文章汇总

点云分析

Point Cloud Analysis

1. Adaptive Hierarchical Down-Sampling for Point Cloud Classification
2. PointAugment: An Auto-Augmentation Framework for Point Cloud Classification
3. Convolution in the Cloud: Learning Deformable Kernels in 3D Graph Convolution Networks for Point Cloud Analysis
4. FPConv: Learning Local Flattening for Point Convolution
5. Global-Local Bidirectional Reasoning for Unsupervised Representation Learning of 3D Point Clouds
6. PointASNL: Robust Point Clouds Processing Using Nonlocal Neural Networks With Adaptive Sampling
7. Grid-GCN for Fast and Scalable Point Cloud Learning
8. SampleNet: Differentiable Point Cloud Sampling
9. Going Deeper With Lean Point Networks
10. LG-GAN: Label Guided Adversarial Network for Flexible Targeted Attack of Point Cloud Based Deep Networks
11. Neural Implicit Embedding for Point Cloud Analysis
12. PointGMM: A Neural GMM Network for Point Clouds

Normal Estimation

1. Geometry and Learning Co-Supported Normal Estimation for Unstructured Point Cloud

3D 目标检测

3D Object Detection

1. SSRNet: Scalable 3D Surface Reconstruction Network
2. HVNet: Hybrid Voxel Network for LiDAR Based 3D Object Detection
3. Point-GNN: Graph Neural Network for 3D Object Detection in a Point Cloud
4. Joint 3D Instance Segmentation and Object Detection for Autonomous Driving
5. ImVoteNet: Boosting 3D Object Detection in Point Clouds With Image Votes
6. PointPainting: Sequential Fusion for 3D Object Detection
7. End-to-End Pseudo-LiDAR for Image-Based 3D Object Detection
8. P2B: Point-to-Box Network for 3D Object Tracking in Point Clouds
9. PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detection
10. Structure Aware Single-Stage 3D Object Detection From Point Cloud
11. Physically Realizable Adversarial Examples for LiDAR Object Detection
12. Associate-3Ddet: Perceptual-to-Conceptual Association for 3D Point Cloud Object Detection
13. LiDAR-Based Online 3D Video Object Detection With Graph-Based Message Passing and Spatiotemporal Transformer Attention
14. SESS: Self-Ensembling Semi-Supervised 3D Object Detection
15. What You See is What You Get: Exploiting Visibility for 3D Object Detection
16. MLCVNet: Multi-Level Context VoteNet for 3D Object Detection
17. Density-Based Clustering for 3D Object Detection in Point Clouds

3D 目标跟踪

1. GNN3DMOT: Graph Neural Network for 3D Multi-Object Tracking With 2D-3D Multi-Feature Learning

3D 语义分割

3D Semantic Segmentation on Point Clouds

1. Multi-Path Region Mining for Weakly Supervised 3D Semantic Segmentation on Point Clouds
2. Few-Shot Learning of Part-Specific Probability Space for 3D Shape Segmentation
3. Fusion-Aware Point Convolution for Online Semantic 3D Scene Segmentation
4. SpSequenceNet: Semantic Segmentation Network on 4D Point Clouds
5. PointGroup: Dual-Set Point Grouping for 3D Instance Segmentation
6. 3D-MPA: Multi-Proposal Aggregation for 3D Semantic Instance Segmentation
7. Weakly Supervised Semantic Point Cloud Segmentation: Towards 10x Fewer Labels
8. End-to-End 3D Point Cloud Instance Segmentation Without Detection
9. xMUDA: Cross-Modal Unsupervised Domain Adaptation for 3D Semantic Segmentation
10. Learning to Segment 3D Point Clouds in 2D Image Space
11. SegGCN: Efficient 3D Point Cloud Segmentation With Fuzzy Spherical Kernel
12. RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Clouds
13. PolarNet: An Improved Grid Representation for Online LiDAR Point Clouds Semantic Segmentation
14. Unsupervised Learning of Intrinsic Structural Representation Points

3D 重建

3D Reconstruction

1. A Hierarchical Graph Network for 3D Object Detection on Point Clouds
2. Shape Reconstruction by Learning Differentiable Surface Representations
3. Connect-and-Slice: An Hybrid Approach for Reconstructing 3D Objects
4. Learning 3D Semantic Scene Graphs From 3D Indoor Reconstructions

点云补全

Point Cloud Completion

1. Cascaded Refinement Network for Point Cloud Completion
2. Point Cloud Completion by Skip-Attention Network With Hierarchical Folding
3. Implicit Functions in Feature Space for 3D Shape Reconstruction and Completion
4. PF-Net: Point Fractal Network for 3D Point Cloud Completion

3D Registration

1. Learning Multiview 3D Point Cloud Registration
2. 3DRegNet: A Deep Neural Network for 3D Point Registration
3. Global Optimality for Point Set Registration Using Semidefinite Programming
4. Feature-Metric Registration: A Fast Semi-Supervised Approach for Robust Point Cloud Registration Without Correspondences
5. D3Feat: Joint Learning of Dense Detection and Description of 3D Local Features
6. Unsupervised Deep Shape Descriptor With Point Distribution Learning
7. End-to-End Learning Local Multi-View Descriptors for 3D Point Clouds

未分类

1. Upgrading Optical Flow to 3D Scene Flow Through Optical Expansion
2. C-Flow: Conditional Generative Flow Models for Images and 3D Point Clouds
3. From Image Collections to Point Clouds With Self-Supervised Shape and Pose Networks
4. An Efficient PointLSTM for Point Clouds Based Gesture Recognition
5. Sequential 3D Human Pose and Shape Estimation From Point Clouds
6. Self-Robust 3D Point Recognition via Gather-Vector Guidance
7. On Isometry Robustness of Deep 3D Point Cloud Models Under Adversarial Attacks
8. OctSqueeze: Octree-Structured Entropy Model for LiDAR Compression
9. Neural Point Cloud Rendering via Multi-Plane Projection
10. LiDARsim: Realistic LiDAR Simulation by Leveraging the Real World
11. FroDO: From Detections to 3D Objects