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
- Adaptive Hierarchical Down-Sampling for Point Cloud Classification
- PointAugment: An Auto-Augmentation Framework for Point Cloud Classification
- Convolution in the Cloud: Learning Deformable Kernels in 3D Graph Convolution Networks for Point Cloud Analysis
- FPConv: Learning Local Flattening for Point Convolution
- Global-Local Bidirectional Reasoning for Unsupervised Representation Learning of 3D Point Clouds
- PointASNL: Robust Point Clouds Processing Using Nonlocal Neural Networks With Adaptive Sampling
- Grid-GCN for Fast and Scalable Point Cloud Learning
- SampleNet: Differentiable Point Cloud Sampling
- Going Deeper With Lean Point Networks
- Neural Implicit Embedding for Point Cloud Analysis
- PointGMM: A Neural GMM Network for Point Clouds
Normal Estimation
3D 目标检测
3D Object Detection
- SSRNet: Scalable 3D Surface Reconstruction Network
- HVNet: Hybrid Voxel Network for LiDAR Based 3D Object Detection
- Point-GNN: Graph Neural Network for 3D Object Detection in a Point Cloud
- Joint 3D Instance Segmentation and Object Detection for Autonomous Driving
- ImVoteNet: Boosting 3D Object Detection in Point Clouds With Image Votes
- PointPainting: Sequential Fusion for 3D Object Detection
- End-to-End Pseudo-LiDAR for Image-Based 3D Object Detection
- P2B: Point-to-Box Network for 3D Object Tracking in Point Clouds
- PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detection
- Structure Aware Single-Stage 3D Object Detection From Point Cloud
- Physically Realizable Adversarial Examples for LiDAR Object Detection
- Associate-3Ddet: Perceptual-to-Conceptual Association for 3D Point Cloud Object Detection
- LiDAR-Based Online 3D Video Object Detection With Graph-Based Message Passing and Spatiotemporal Transformer Attention
- SESS: Self-Ensembling Semi-Supervised 3D Object Detection
- What You See is What You Get: Exploiting Visibility for 3D Object Detection
- MLCVNet: Multi-Level Context VoteNet for 3D Object Detection
- Density-Based Clustering for 3D Object Detection in Point Clouds
3D 目标跟踪
3D 语义分割
3D Semantic Segmentation on Point Clouds
- Multi-Path Region Mining for Weakly Supervised 3D Semantic Segmentation on Point Clouds
- Few-Shot Learning of Part-Specific Probability Space for 3D Shape Segmentation
- Fusion-Aware Point Convolution for Online Semantic 3D Scene Segmentation
- SpSequenceNet: Semantic Segmentation Network on 4D Point Clouds
- PointGroup: Dual-Set Point Grouping for 3D Instance Segmentation
- 3D-MPA: Multi-Proposal Aggregation for 3D Semantic Instance Segmentation
- Weakly Supervised Semantic Point Cloud Segmentation: Towards 10x Fewer Labels
- End-to-End 3D Point Cloud Instance Segmentation Without Detection
- xMUDA: Cross-Modal Unsupervised Domain Adaptation for 3D Semantic Segmentation
- Learning to Segment 3D Point Clouds in 2D Image Space
- SegGCN: Efficient 3D Point Cloud Segmentation With Fuzzy Spherical Kernel
- RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Clouds
- PolarNet: An Improved Grid Representation for Online LiDAR Point Clouds Semantic Segmentation
- Unsupervised Learning of Intrinsic Structural Representation Points
3D 重建
3D Reconstruction
- A Hierarchical Graph Network for 3D Object Detection on Point Clouds
- Shape Reconstruction by Learning Differentiable Surface Representations
- Connect-and-Slice: An Hybrid Approach for Reconstructing 3D Objects
- Learning 3D Semantic Scene Graphs From 3D Indoor Reconstructions
点云补全
Point Cloud Completion
- Cascaded Refinement Network for Point Cloud Completion
- Point Cloud Completion by Skip-Attention Network With Hierarchical Folding
- Implicit Functions in Feature Space for 3D Shape Reconstruction and Completion
- PF-Net: Point Fractal Network for 3D Point Cloud Completion
3D Registration
- Learning Multiview 3D Point Cloud Registration
- 3DRegNet: A Deep Neural Network for 3D Point Registration
- Global Optimality for Point Set Registration Using Semidefinite Programming
- Feature-Metric Registration: A Fast Semi-Supervised Approach for Robust Point Cloud Registration Without Correspondences
- D3Feat: Joint Learning of Dense Detection and Description of 3D Local Features
- Unsupervised Deep Shape Descriptor With Point Distribution Learning
- End-to-End Learning Local Multi-View Descriptors for 3D Point Clouds
未分类
- Upgrading Optical Flow to 3D Scene Flow Through Optical Expansion
- C-Flow: Conditional Generative Flow Models for Images and 3D Point Clouds
- From Image Collections to Point Clouds With Self-Supervised Shape and Pose Networks
- An Efficient PointLSTM for Point Clouds Based Gesture Recognition
- Sequential 3D Human Pose and Shape Estimation From Point Clouds
- Self-Robust 3D Point Recognition via Gather-Vector Guidance
- On Isometry Robustness of Deep 3D Point Cloud Models Under Adversarial Attacks
- OctSqueeze: Octree-Structured Entropy Model for LiDAR Compression
- Neural Point Cloud Rendering via Multi-Plane Projection
- LiDARsim: Realistic LiDAR Simulation by Leveraging the Real World
- FroDO: From Detections to 3D Objects
- LG-GAN: Label Guided Adversarial Network for Flexible Targeted Attack of Point Cloud Based Deep Networks