PoseRN: A 2D pose refinement network for bias-free multi-view 3D human pose estimation.
Akihiko SayoDiego ThomasHiroshi KawasakiYuta NakashimaKatsushi IkeuchiPublished in: CoRR (2021)
Keyphrases
- multi view
- d objects
- single view
- multiple views
- depth map
- three dimensional
- camera calibration
- bundle adjustment
- scene reconstruction
- multiple cameras
- multi view images
- pose estimation
- multi view clustering
- range images
- camera parameters
- motion capture
- multi views
- multi view reconstruction
- multiple viewpoints
- view synthesis
- visual hull
- co training
- semi supervised
- face tracking
- multi view stereo
- surface reconstruction
- depth video
- multi view face detection
- pairwise