Robust Pose Transfer with Dynamic Details using Neural Video Rendering.
Yang-Tian SunHao-Zhi HuangXuan WangYu-Kun LaiWei LiuLin GaoPublished in: CoRR (2021)
Keyphrases
- long video sequences
- real time
- illumination variations
- video frames
- neural network
- video sequences
- pose estimation
- pose invariant face recognition
- partial occlusion
- video surveillance
- robust recognition
- network architecture
- video content
- video data
- dynamic environments
- key frames
- dynamic scenes
- person detection
- human activities
- space time
- dynamic textures
- high definition
- object pose
- d objects
- high quality
- illumination invariance