GPT-Connect: Interaction between Text-Driven Human Motion Generator and 3D Scenes in a Training-free Manner.
Haoxuan QuZiyan GuoJun LiuPublished in: CoRR (2024)
Keyphrases
- human motion
- d scene
- human body
- motion capture
- image sequences
- single image
- video sequences
- depth map
- image based rendering
- optical motion capture
- spatio temporal
- body parts
- motion sequences
- motion recognition
- optical flow
- moving camera
- motion capture data
- human actions
- human computer interaction
- scene structure
- photorealistic
- training set
- human movements
- realistic rendering
- computer vision
- visual data
- machine learning
- view dependent
- three dimensional