Unsupervised Coherent Video Cartoonization with Perceptual Motion Consistency.
Zhenhuan LiuLiang LiHuajie JiangXin JinDandan TuShuhui WangZheng-Jun ZhaPublished in: AAAI (2022)
Keyphrases
- temporal consistency
- space time
- key frames
- temporal filtering
- video sequences
- object motion
- successive frames
- motion features
- video data
- visual perception
- spatial and temporal
- input video
- low frame rate
- moving camera
- unsupervised manner
- motion analysis
- video representation
- static images
- image sequences
- dynamic scenes
- visual data
- reference frame
- motion estimation
- visual cues
- video objects
- motion patterns
- motion model
- video footage
- shot change detection
- video content
- unsupervised learning
- multimedia
- image frames
- layered representation
- motion trajectories
- periodic motion
- surveillance videos
- spatio temporal
- camera motion
- video frames
- motion segmentation
- low level
- semi supervised
- video scene
- perceptual information
- temporal continuity
- video summarization
- wide area motion imagery
- optical flow
- motion capture data
- human motion
- video signals
- global motion
- motion capture
- visual input
- video streams
- perceptual quality
- particle filter
- camera movement
- human actions
- temporal coherence
- single frame
- video clips