Unsupervised Image Super-Resolution with an Indirect Supervised Path
By Zhen-Wen Han, Enyan Dai, Xu Jia, Xiaoyi Ren, Shuaijun Chen, Chunjing Xu, Jianzhuang Liu, Qi Tian. 2019
49 citations recorded by the source corpus.
The task of single image super-resolution (SISR) aims at reconstructing a high-resolution (HR) image from a low- resolution (LR) image. Although significant progress has been made with deep learning models, they are trained on synthetic paired data in a supervised way and do not perform well on real cases. There are several attempts that directly apply unsupervised image translation models to address such a problem. However, unsupervised image translation models need to be modified to adapt to unsupervised low-level vision task which poses higher requirement on the accuracy of translation. In this work, we propose a novel framework which is composed of two stages: 1) unsupervised image translation between real LR and synthetic LR images; 2) supervised super-resolution from approximated real LR images to the paired HR images. It takes the synthetic LR images as a bridge and creates an indirect supervised path. We show that our framework is so flexible that any unsupervised translation model and deep learning based super-resolution model can be integrated into it. Besides, a collaborative training strategy is proposed to encourage the two stages collaborate with each other for better degradation learning and super-resolution performance. The proposed method achieves very good performance on datasets of NTIRE 2017, NTIRE 2018 and NTIRE 2020, even comparable with supervised methods.
Subfields: Computer Vision and Pattern Recognition, Media Technology
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Computer Vision and Pattern Recognition
- Radu Timofte
- Luc Van Gool
- Martin Danelljan
- Andreas Lugmayr
- Kyung-ah Sohn
- Namhyuk Ahn
- Ming-Hsuan Yang
- Christian Micheloni
In Media Technology
- Kyung-ah Sohn
- Namhyuk Ahn
- Radu Timofte
- Martin Danelljan
- Andreas Lugmayr
- Mostafa El-Khamy
- Jungwon Lee
- Haoyu Ren
Citations in the corpus
- VEGA: Towards an End-to-End Configurable AutoML Pipeline (2020, neutral): “CycleSR (Chen et al., 2020).”
- Real-World Single Image Super-Resolution: A Brief Review (2021, methodology): “ISPUSR CVPRW-2020 [110] Domain translation-based Unsupervised image translation, Supervised SR, Collaborative training”
- NTIRE 2020 Challenge on Real-World Image Super-Resolution: Methods and Results (2020, methodology): “This method, which is detailed in [10], adopts the idea of learning the degradation operator in order to synthetically generate paired training data for SR network.”