VTP: Volumetric Transformer for Multi-view Multi-person 3D Pose Estimation.
Yuxing ChenRenshu GuOuhan HuangGangyong JiaPublished in: CoRR (2022)
Keyphrases
- multi view
- three dimensional
- single view
- d objects
- pose estimation
- multiple views
- range data
- depth map
- camera calibration
- range images
- articulated objects
- multiple cameras
- multi view reconstruction
- shape from silhouettes
- dynamic scenes
- semi supervised
- motion capture
- surface reconstruction
- multi view images
- co training
- multi view clustering
- multi view learning
- visual hull
- multi view stereo
- scene reconstruction
- view synthesis
- multiple viewpoints
- surface representation
- free viewpoint
- light field
- depth video
- particle filtering