Deep Unfolding Network for Image Super-Resolution

Learning-based single image super-resolution (SISR) methods are continuously showing superior effectiveness and efficiency over traditional model-based methods, largely due to the end-to-end training. However, different from model-based methods that can handle the SISR problem with different scale f...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Proceedings (IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Online) s. 3214 - 3223
Hlavní autoři: Zhang, Kai, Van Gool, Luc, Timofte, Radu
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IEEE 01.01.2020
Témata:
Computational modeling
Degradation
Image resolution
Inference algorithms
Kernel
Learning systems
Noise level
ISSN:1063-6919
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Learning-based single image super-resolution (SISR) methods are continuously showing superior effectiveness and efficiency over traditional model-based methods, largely due to the end-to-end training. However, different from model-based methods that can handle the SISR problem with different scale factors, blur kernels and noise levels under a unified MAP (maximum a posteriori) framework, learning-based methods generally lack such flexibility. To address this issue, this paper proposes an end-to-end trainable unfolding network which leverages both learningbased methods and model-based methods. Specifically, by unfolding the MAP inference via a half-quadratic splitting algorithm, a fixed number of iterations consisting of alternately solving a data subproblem and a prior subproblem can be obtained. The two subproblems then can be solved with neural modules, resulting in an end-to-end trainable, iterative network. As a result, the proposed network inherits the flexibility of model-based methods to super-resolve blurry, noisy images for different scale factors via a single model, while maintaining the advantages of learning-based methods. Extensive experiments demonstrate the superiority of the proposed deep unfolding network in terms of flexibility, effectiveness and also generalizability.
ISSN:1063-6919
DOI:10.1109/CVPR42600.2020.00328