Dual Circle Contrastive Learning-Based Blind Image Super-Resolution
- 21 July 2023
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 34 (3) , 1757-1771
Abstract
Blind image super-resolution (BISR) aims to construct high-resolution image from low-resolution (LR) image that contains unknown degradation. Although the previous methods demonstrated impressive performance by introducing the degradation representation in BISR task, there still exist two problems in most of them. First, they ignore the degradation characteristics of different image regions when generating degradation representation. Second, they lack effective supervision on the generation of both degradation representation and super-resolution result. To solve these problems, we propose the dual circle contrastive learning (DCCL) with the high-efficiency modules to implement BISR. In our proposed method, we design the degradation extraction network to obtain the degradation representations from different texture regions of LR image. Meanwhile, we propose DCCL coupled with the degrading network to guarantee the obtained degradation representation to contain the degradation of LR image as much as possible. The application of DCCL also makes the SR results contain degradation as little as possible. Additionally, we develop an information distillation module for our proposed BISR model to guarantee the SR images with high quality. The experimental results demonstrate that our proposed method achieves the state-of-the-art BISR performance.Keywords
Funding Information
- National Natural Science Foundation of China (U20A20184)
- Natural Science Foundation of Sichuan Province (2023NSFSC1972)
- CAAI-Huawei MindSpore Open Fund (CAAIXSJLJJ-2022-060A)
This publication has 57 references indexed in Scilit:
- Efficient and Degradation-Adaptive Network for Real-World Image Super-Resolution2022
- ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design2018
- Image Super-Resolution Using Very Deep Residual Channel Attention Networks2018
- Residual Dense Network for Image Super-Resolution2018
- Deep Back-Projection Networks for Super-Resolution2018
- Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network2017
- Image Super-Resolution via Deep Recursive Residual Network2017
- Deep Laplacian Pyramid Networks for Fast and Accurate Super-Resolution2017
- Deeply-Recursive Convolutional Network for Image Super-Resolution2016
- Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network2016