Hybrid attention transformer with re-parameterized large kernel convolution for image super-resolution.
Zhicheng MaZhaoxiang LiuKai WangShiguo LianPublished in: Image Vis. Comput. (2024)
Keyphrases
- image super resolution
- kernel regression
- convolution kernel
- dictionary learning
- super resolution
- low resolution
- image registration
- regression model
- low resolution images
- edge preserving
- high resolution
- feature space
- image processing
- maximum a posteriori
- map estimation
- image patches
- kernel function
- support vector
- multiscale
- high quality