Move as You Say, Interact as You Can: Language-guided Human Motion Generation with Scene Affordance.
Zan WangYixin ChenBaoxiong JiaPuhao LiJinlu ZhangJingze ZhangTengyu LiuYixin ZhuWei LiangSiyuan HuangPublished in: CoRR (2024)
Keyphrases
- human motion
- video sequences
- image sequences
- motion capture
- human body
- spatio temporal
- optical motion capture
- visual data
- d scene
- motion capture data
- human motion tracking
- motion sequences
- motion recognition
- moving objects
- body parts
- human movements
- human actions
- human movement
- physical objects
- gait recognition
- three dimensional
- space time
- scene structure
- video frames
- articulated motion
- input image
- scene analysis
- video data
- motion synthesis
- computer vision
- scene understanding
- motion patterns
- humanoid robot
- dynamic scenes
- degrees of freedom