Voxel or Pillar: Exploring Efficient Point Cloud Representation for 3D Object Detection.
Yuhao HuangSanping ZhouJunjie ZhangJinpeng DongNanning ZhengPublished in: AAAI (2024)
Keyphrases
- d objects
- point cloud
- real world objects
- three dimensional
- cad model
- multi view
- surface skeleton
- viewpoint
- object recognition
- multiple views
- pose estimation
- shape descriptors
- structure from motion
- surface reconstruction
- point sets
- topological information
- cad models
- physically plausible
- range data
- d mesh
- computer vision
- control points
- surface patches
- object detection
- knn