Back to Search
Start Over
Image super-resolution by learning weighted convolutional sparse coding
- Source :
- Signal, Image and Video Processing. 15:967-975
- Publication Year :
- 2021
- Publisher :
- Springer Science and Business Media LLC, 2021.
-
Abstract
- Single image super-resolution (SISR) has witnessed substantial progress recently by deep learning-based methods, due to the data-driven end-to-end training. However, most existing DL-based models are built intuitively, with little thought on priors. And the lack of interpretability limits their further improvements. To avoid this, this paper presents an end-to-end trainable unfolding network which leverages both DL- and prior-based methods. Specifically, we introduce the reweighted algorithm into CSC model and solve it by learning weighted iterative soft thresholding algorithm in a convolutional manner. Based on this, we present a SISR model by learning weighted convolutional sparse coding, in which the channel attention is resorted to learn the weight. Extensive experiments demonstrate the superiority of our method to recent state-of-the-art SISR methods, in terms of both quantitative and qualitative results.
- Subjects :
- Soft thresholding
Channel (digital image)
Computer science
business.industry
Deep learning
020206 networking & telecommunications
Pattern recognition
02 engineering and technology
Superresolution
Image (mathematics)
Signal Processing
Prior probability
0202 electrical engineering, electronic engineering, information engineering
020201 artificial intelligence & image processing
Artificial intelligence
Electrical and Electronic Engineering
Neural coding
business
Interpretability
Subjects
Details
- ISSN :
- 18631711 and 18631703
- Volume :
- 15
- Database :
- OpenAIRE
- Journal :
- Signal, Image and Video Processing
- Accession number :
- edsair.doi...........9b441ab33bde789054deafb382adc22b