CVPR-2020-point-cloud-analysis

CVPR 2020 papers focusing on point cloud analysis

• D3Feat: Joint Learning of Dense Detection and Description of 3D Local Features

  • [Code]

• RPM-Net: Robust Point Matching using Learned Features

  • [Code]

• D3VO: Deep Depth, Deep Pose and Deep Uncertainty for Monocular Visual Odometry

• Cascaded Refinement Network for Point Cloud Completion

  • [Code]

• PointAugment: an Auto-Augmentation Framework for Point Cloud Classification

  • [Code]

• Weakly Supervised Semantic Point Cloud Segmentation: Towards 10x Fewer Labels. segmention

  • [Code]

• Neural Implicit Embedding for Point Cloud Analysis. segmention classification

  • [Code]

• OctSqueeze: Octree-Structured Entropy Model for LiDAR Compression. compression oral

• PF-Net: Point Fractal Network for 3D Point Cloud Completion completion

  • [Code]

• End-to-End Pseudo-LiDAR for Image-Based 3D Object Detection

  • [Code]

• Going Deeper with Point Networks segmentation

  • [Code]

• Learning multiview 3D point cloud registration

• Geometry and Learning Co-supported Normal Estimation for UnstructuredPoint Cloud. normal estimation

• LG-GAN: Label Guided Adversarial Network for Flexible Targeted Attack of Point Cloud-based Deep Networks. attack

  • [Code]

• On Isometry Robustness of Deep 3D Point Cloud Models Under Adversarial Attacks. attack

  • [Code]

• Convolution in the Cloud: Learning Deformable Kernels in 3D Graph Convolution Networks for Point Cloud Analysis. classification segmentation

  • [Code]

• An Efficient PointLSTM for Point Clouds Based Gesture Recognition. Gesture Recognition

  • [Code]

• Total3DUnderstanding: Joint Layout, Object Pose and Mesh Reconstruction for Indoor Scenes from a Single Image

• In Perfect Shape: Certifiably Optimal 3D Shape Reconstruction from 2D Landmarks

• Unsupervised Learning of Intrinsic Structural Representation Points

  • [Code]

• LiDAR-based Online 3D Video Object Detection with Graph-based Message Passing and Spatiotemporal Transformer Attention

  • [Code]

• RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Clouds segmentation

  • [Code]

• C-Flow: Conditional Generative Flow Models for Images and 3D Point Clouds

• High-dimensional Convolutional Networks for Geometric Pattern Recognition. registrition oral

  • [Code]

• Representations, Metrics and Statistics For Shape Analysis of Elastic Graphs

• PointGroup: Dual-Set Point Grouping for 3D Instance Segmentation

  • [Code]

• Implicit Functions in Feature Space for 3D Shape Reconstruction and Completion

  • [Code]

• Feature-metric Registration: A Fast Semi-supervised Approach for Robust Point Cloud Registration without Correspondences

  • [Code]

• From Image Collections to Point Clouds with Self-supervised Shape and Pose Networks

  • [Code]

• Associate-3Ddet: Perceptual-to-Conceptual association for 3D Point Cloud Object Detection detection

  • [Code]

• Point-GNN: Graph Neural Network for 3D Object Detection in a Point Cloud detection

  • [Code]

• PointGMM: a Neural GMM Network for Point Clouds

  • [Code]

• 3D-MPA: Multi Proposal Aggregation for 3D Semantic Instance Segmentation

  • [Code]

• PointPainting: Sequential Fusion for 3D Object Detection detection

  • [Code]

• Point Cloud Completion by Skip-attention Network with Hierarchical Folding completion

• PointASNL: Robust Point Clouds Processing using Nonlocal Neural Networks with Adaptive Sampling. classification segmentation

  • [Code]

• PolarNet: An Improved Grid Representation for Online LiDAR Point Clouds Semantic Segmentation. segmentation

  • [Code]

• Grid-GCN for Fast and Scalable Point Cloud Learning. learning

  • [Code]

• End-to-End Learning Local Multi-View Descriptors for 3D Point Clouds. Registration

  • [Code]

• On Isometry Robustness of Deep 3D Point Cloud Models Under Adversarial Attacks. attack

  • [Code]

• SampleNet: Differentiable Point Cloud Sampling. sampling

  • [Code]

• SegGCN: Efficient 3D Point Cloud Segmentation With Fuzzy Spherical Kernel. segmentation

  • [Code]

• ImVoteNet: Boosting 3D Object Detection in Point Clouds with Image Votes. Detection

  • [Code]

• P2B: Point-to-Box Network for 3D Object Tracking in Point Clouds. Tracking Oral

  • [Code]