Video Autoencoder: self-supervised disentanglement of static 3D structure and motion.
Zihang LaiSifei LiuAlexei A. EfrosXiaolong WangPublished in: CoRR (2021)
Keyphrases
- space time
- spatial and temporal
- image sequences
- moving camera
- motion estimation
- temporal filtering
- temporal structure
- video sequences
- video data
- video representation
- key frames
- moving objects
- object motion
- dynamic scenes
- geometric structure
- multimedia
- motion patterns
- motion detection
- video retrieval
- motion analysis
- temporal information
- motion segmentation
- visual data
- human motion
- static images
- temporal coherence
- temporal consistency
- video frames
- successive frames
- temporal domain
- spatio temporal
- video footage
- learning algorithm
- shot change detection