4D Human Body Capture from Egocentric Video via 3D Scene Grounding.
Miao LiuDexin YangYan ZhangZhaopeng CuiJames M. RehgSiyu TangPublished in: CoRR (2020)
Keyphrases
- human body
- d scene
- pedestrian detection
- body parts
- single image
- depth map
- pose estimation
- human motion
- scene understanding
- video data
- video frames
- video sequences
- three dimensional
- image based rendering
- photorealistic
- optical flow
- articulated objects
- camera parameters
- view synthesis
- activity recognition
- multi view
- human pose
- stereo vision
- motion estimation
- dynamic scenes
- computer vision
- human detection
- machine learning