Deep Semantic Graph Transformer for Multi-View 3D Human Pose Estimation.
Lijun ZhangKangkang ZhouFeng LuXiang-Dong ZhouYu ShiPublished in: AAAI (2024)
Keyphrases
- multi view
- single view
- multiple views
- three dimensional
- d objects
- depth map
- camera calibration
- multi view clustering
- surface reconstruction
- semi supervised
- bundle adjustment
- stereo video
- scene reconstruction
- multi view stereo
- multiple viewpoints
- range images
- multi view learning
- scene flow estimation
- multi view face detection
- multi view reconstruction
- multi view images
- co training
- multiple cameras
- body parts
- view synthesis
- similarity measure