A l1-norm preserving motion-compensated transform for sparse approximation of image sequences.
Markus FlierlPublished in: ICASSP (2010)
Keyphrases
- motion compensated
- sparse approximation
- image sequences
- motion estimation
- motion field
- coding gain
- residual signal
- motion compensation
- linear combination
- video coding
- optical flow
- noise model
- sparse coding
- prediction error
- motion vectors
- gaussian process
- motion model
- convex relaxation
- video sequences
- super resolution
- spatial domain
- three dimensional
- inter frame
- object recognition
- image classification
- globally optimal
- computational complexity
- high resolution