# Criteria Comparative Learning for Real-scene Image Super-Resolution

arXiv: https://arxiv.org/abs/2207.12767 · HTML: https://mlsanity.com/paper/2207.12767/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 42 of its 59 references that are in the map.
- First posted on arXiv 26 Jul 2022.

## Builds on (most cited first, 30 of 42)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Supervised Contrastive Learning](https://mlsanity.com/paper/2004.11362/) (2020)
- [Learning Deep Features for Discriminative Localization](https://mlsanity.com/paper/1512.04150/) (2015)
- [Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network](https://mlsanity.com/paper/1609.04802/) (2016)
- [SwinIR: Image Restoration Using Swin Transformer](https://mlsanity.com/paper/2108.10257/) (2021)
- [Enhanced Deep Residual Networks for Single Image Super-Resolution](https://mlsanity.com/paper/1707.02921/) (2017)
- [Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hypersphere](https://mlsanity.com/paper/2005.10242/) (2020)
- [ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks](https://mlsanity.com/paper/1809.00219/) (2018)
- [Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Data](https://mlsanity.com/paper/2107.10833/) (2021)
- [Contrastive Learning for Unpaired Image-to-Image Translation](https://mlsanity.com/paper/2007.15651/) (2020)
- [Designing a Practical Degradation Model for Deep Blind Image Super-Resolution](https://mlsanity.com/paper/2103.14006/) (2021)
- [Toward Real-World Single Image Super-Resolution: A New Benchmark and A New Model](https://mlsanity.com/paper/1904.00523/) (2019)
- ["Zero-Shot" Super-Resolution using Deep Internal Learning](https://mlsanity.com/paper/1712.06087/) (2017)
- [Component Divide-and-Conquer for Real-World Image Super-Resolution](https://mlsanity.com/paper/2008.01928/) (2020)
- [Blind Super-Resolution Kernel Estimation using an Internal-GAN](https://mlsanity.com/paper/1909.06581/) (2019)
- [Unsupervised Image Super-Resolution using Cycle-in-Cycle Generative Adversarial Networks](https://mlsanity.com/paper/1809.00437/) (2018)
- [Frequency Separation for Real-World Super-Resolution](https://mlsanity.com/paper/1911.07850/) (2019)
- [Bringing Old Photos Back to Life](https://mlsanity.com/paper/2004.09484/) (2020)
- [Unsupervised Real-world Image Super Resolution via Domain-distance Aware Training](https://mlsanity.com/paper/2004.01178/) (2020)
- [NTIRE 2020 Challenge on Real-World Image Super-Resolution: Methods and Results](https://mlsanity.com/paper/2005.01996/) (2020)
- [Knowledge-Guided Multi-Label Few-Shot Learning for General Image Recognition](https://mlsanity.com/paper/2009.09450/) (2020)
- [Unpaired Deep Image Deraining Using Dual Contrastive Learning](https://mlsanity.com/paper/2109.02973/) (2021)
- [Camera Lens Super-Resolution](https://mlsanity.com/paper/1904.03378/) (2019)
- [Channel-wise and Spatial Feature Modulation Network for Single Image Super-Resolution](https://mlsanity.com/paper/1809.11130/) (2018)
- [AIM 2019 Challenge on Real-World Image Super-Resolution: Methods and Results](https://mlsanity.com/paper/1911.07783/) (2019)

## Built on by (most cited first, 8 of 8)

- [Ultra-High-Definition Image Restoration: New Benchmarks and A Dual Interaction Prior-Driven Solution](https://mlsanity.com/paper/2406.13607/) (2024)
- [IDF-CR: Iterative Diffusion Process for Divide-and-Conquer Cloud Removal in Remote-sensing Images](https://mlsanity.com/paper/2403.11870/) (2024)
- [Learning from Multi-Perception Features for Real-Word Image Super-resolution](https://mlsanity.com/paper/2305.18547/) (2023)
- [Bridging Fidelity-Reality with Controllable One-Step Diffusion for Image Super-Resolution](https://mlsanity.com/paper/2512.14061/) (2025)
- [DnSwin: Toward Real-World Denoising via Continuous Wavelet Sliding-Transformer](https://mlsanity.com/paper/2207.13861/) (2022)
- [Learning A Coarse-to-Fine Diffusion Transformer for Image Restoration](https://mlsanity.com/paper/2308.08730/) (2023)
- [HiREN: Towards Higher Supervision Quality for Better Scene Text Image Super-Resolution](https://mlsanity.com/paper/2307.16410/) (2023)
- [AngularFuse: A Closer Look at Angle-based Perception for Spatial-Sensitive Multi-Modality Image Fusion](https://mlsanity.com/paper/2510.12260/) (2025)

## Abstract (arXiv)

Real-scene image super-resolution aims to restore real-world low-resolution images into their high-quality versions. A typical RealSR framework usually includes the optimization of multiple criteria which are designed for different image properties, by making the implicit assumption that the ground-truth images can provide a good trade-off between different criteria. However, this assumption could be easily violated in practice due to the inherent contrastive relationship between different image properties. Contrastive learning (CL) provides a promising recipe to relieve this problem by learning discriminative features using the triplet contrastive losses. Though CL has achieved significant success in many computer vision tasks, it is non-trivial to introduce CL to RealSR due to the difficulty in defining valid positive image pairs in this case. Inspired by the observation that the contrastive relationship could also exist between the criteria, in this work, we propose a novel training paradigm for RealSR, named Criteria Comparative Learning (Cria-CL), by developing contrastive losses defined on criteria instead of image patches. In addition, a spatial projector is proposed to obtain a good view for Cria-CL in RealSR. Our experiments demonstrate that compared with the typical weighted regression strategy, our method achieves a significant improvement under similar parameter settings.