A method for single frame super resolution with inpainting based on sparse dictionary learning.
Takuya UmeharaKazushi MimuraAkira HirabayashiPublished in: APSIPA (2014)
Keyphrases
- multiscale
- single frame
- super resolution
- image super resolution
- dictionary learning
- low resolution images
- image restoration
- multi frame
- high resolution images
- low resolution
- resolution enhancement
- image segmentation
- single image super resolution
- video sequences
- sparse representation
- video frames
- sparse coding
- high resolution
- motion estimation
- optical flow
- pairwise
- high quality
- computationally efficient
- input data
- similarity measure