CVPR 2019-Point cloud with code

추후에 읽어 보려고 Paper with code에 공개된 CVPR2019 논문중에서 Point cloud(LIDAR, RGB-D)와 관련된 논문들만 모아 보았습니다.

3D Detection, Segmentation

• PointRCNN: 3D Object Proposal Generation and Detection from Point Cloud

• PointPillars: Fast Encoders for Object Detection from Point Clouds

• PointConv: Deep Convolutional Networks on 3D Point Clouds

• Associatively Segmenting Instances and Semantics in Point Clouds

• 3D-SIS: 3D Semantic Instance Segmentation of RGB-D Scans

• Relation-Shape Convolutional Neural Network for Point Cloud Analysis

Registration & Reconstruction

• PointNetLK: Robust & Efficient Point Cloud Registration using PointNet

• Scan2CAD: Learning CAD Model Alignment in RGB-D Scans

• The Perfect Match: 3D Point Cloud Matching with Smoothed Densities

Pose Estimation

• DenseFusion: 6D Object Pose Estimation by Iterative Dense Fusion

Upsampling

• Pseudo-LiDAR from Visual Depth Estimation: Bridging the Gap in 3D Object Detection for Autonomous Driving

• Patch-based Progressive 3D Point Set Upsampling

일부 논문들의 발표는 [이곳]에서 볼 수 있습니다. 일부 논문들의 포스트는 [이곳]에서 볼 수 있습니다.