VTP: volumetric transformer for multi-view multi-person 3D pose estimation.
Yuxing ChenRenshu GuOuhan HuangGangyong JiaPublished in: Appl. Intell. (2023)
Keyphrases
- multi view
- three dimensional
- d objects
- single view
- pose estimation
- multiple views
- depth map
- range data
- camera calibration
- multiple cameras
- range images
- dynamic scenes
- articulated objects
- scene reconstruction
- multi view reconstruction
- semi supervised
- multi view learning
- view synthesis
- light field
- multiple viewpoints
- bundle adjustment
- surface reconstruction
- multi view clustering
- rigid objects
- motion capture
- co training
- geometric constraints
- particle filtering
- pairwise