# Closed-loop Matters: Dual Regression Networks for Single Image Super-Resolution

arXiv: https://arxiv.org/abs/2003.07018 · HTML: https://mlsanity.com/paper/2003.07018/

## Key facts

- Cited by 90 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Mar 2020.

## Built on by (most cited first, 30 of 90)

- [SwinIR: Image Restoration Using Swin Transformer](https://mlsanity.com/paper/2108.10257/) (2021)
- [SRDiff: Single Image Super-Resolution with Diffusion Probabilistic Models](https://mlsanity.com/paper/2104.14951/) (2021)
- [Towards Real-World Blind Face Restoration with Generative Facial Prior](https://mlsanity.com/paper/2101.04061/) (2021)
- [VRT: A Video Restoration Transformer](https://mlsanity.com/paper/2201.12288/) (2022)
- [Video Super-Resolution Transformer](https://mlsanity.com/paper/2106.06847/) (2021)
- [Intriguing Findings of Frequency Selection for Image Deblurring](https://mlsanity.com/paper/2111.11745/) (2021)
- [Flow-based Kernel Prior with Application to Blind Super-Resolution](https://mlsanity.com/paper/2103.15977/) (2021)
- [CiaoSR: Continuous Implicit Attention-in-Attention Network for Arbitrary-Scale Image Super-Resolution](https://mlsanity.com/paper/2212.04362/) (2022)
- [Real-World Single Image Super-Resolution: A Brief Review](https://mlsanity.com/paper/2103.02368/) (2021)
- [DreamClear: High-Capacity Real-World Image Restoration with Privacy-Safe Dataset Curation](https://mlsanity.com/paper/2410.18666/) (2024)
- [Countering Malicious DeepFakes: Survey, Battleground, and Horizon](https://mlsanity.com/paper/2103.00218/) (2021)
- [Reference-based Image Super-Resolution with Deformable Attention Transformer](https://mlsanity.com/paper/2207.11938/) (2022)
- [NTIRE 2021 Challenge on Image Deblurring](https://mlsanity.com/paper/2104.14854/) (2021)
- [Blind Image Super-Resolution via Contrastive Representation Learning](https://mlsanity.com/paper/2107.00708/) (2021)
- [NTIRE 2021 Challenge on Quality Enhancement of Compressed Video: Methods and Results](https://mlsanity.com/paper/2104.10781/) (2021)
- [COMISR: Compression-Informed Video Super-Resolution](https://mlsanity.com/paper/2105.01237/) (2021)
- [DVMSR: Distillated Vision Mamba for Efficient Super-Resolution](https://mlsanity.com/paper/2405.03008/) (2024)
- [Enriched CNN-Transformer Feature Aggregation Networks for Super-Resolution](https://mlsanity.com/paper/2203.07682/) (2022)
- [A Systematic Survey of Deep Learning-based Single-Image Super-Resolution](https://mlsanity.com/paper/2109.14335/) (2021)
- [A Dynamic Residual Self-Attention Network for Lightweight Single Image Super-Resolution](https://mlsanity.com/paper/2112.04488/) (2021)
- [CTCNet: A CNN-Transformer Cooperation Network for Face Image Super-Resolution](https://mlsanity.com/paper/2204.08696/) (2022)
- [Structure-Preserving Image Super-Resolution](https://mlsanity.com/paper/2109.12530/) (2021)
- [PUFA-GAN: A Frequency-Aware Generative Adversarial Network for 3D Point Cloud Upsampling](https://mlsanity.com/paper/2203.00914/) (2022)
- [Multi-scale frequency separation network for image deblurring](https://mlsanity.com/paper/2206.00798/) (2022)
- [Efficient Test-Time Adaptation for Super-Resolution with Second-Order Degradation and Reconstruction](https://mlsanity.com/paper/2310.19011/) (2023)
- [Remote Sensing Image Super-resolution and Object Detection: Benchmark and State of the Art](https://mlsanity.com/paper/2111.03260/) (2021)
- [Recurrent Structure Attention Guidance for Depth Super-Resolution](https://mlsanity.com/paper/2301.13419/) (2023)
- [Invertible Rescaling Network and Its Extensions](https://mlsanity.com/paper/2210.04188/) (2022)
- [Structure Flow-Guided Network for Real Depth Super-Resolution](https://mlsanity.com/paper/2301.13416/) (2023)
- [RankSRGAN: Super Resolution Generative Adversarial Networks with Learning to Rank](https://mlsanity.com/paper/2107.09427/) (2021)

## Abstract (arXiv)

Deep neural networks have exhibited promising performance in image super-resolution (SR) by learning a nonlinear mapping function from low-resolution (LR) images to high-resolution (HR) images. However, there are two underlying limitations to existing SR methods. First, learning the mapping function from LR to HR images is typically an ill-posed problem, because there exist infinite HR images that can be downsampled to the same LR image. As a result, the space of the possible functions can be extremely large, which makes it hard to find a good solution. Second, the paired LR-HR data may be unavailable in real-world applications and the underlying degradation method is often unknown. For such a more general case, existing SR models often incur the adaptation problem and yield poor performance. To address the above issues, we propose a dual regression scheme by introducing an additional constraint on LR data to reduce the space of the possible functions. Specifically, besides the mapping from LR to HR images, we learn an additional dual regression mapping estimates the down-sampling kernel and reconstruct LR images, which forms a closed-loop to provide additional supervision. More critically, since the dual regression process does not depend on HR images, we can directly learn from LR images. In this sense, we can easily adapt SR models to real-world data, e.g., raw video frames from YouTube. Extensive experiments with paired training data and unpaired real-world data demonstrate our superiority over existing methods.