# Learning from Multi-Perception Features for Real-Word Image Super-resolution

arXiv: https://arxiv.org/abs/2305.18547 · HTML: https://mlsanity.com/paper/2305.18547/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 42 of its 67 references that are in the map.
- First posted on arXiv 26 May 2023.

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

- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [Supervised Contrastive Learning](https://mlsanity.com/paper/2004.11362/) (2020)
- [Non-local Neural Networks](https://mlsanity.com/paper/1711.07971/) (2017)
- [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)
- [Image Super-Resolution Using Very Deep Residual Channel Attention Networks](https://mlsanity.com/paper/1807.02758/) (2018)
- [ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks](https://mlsanity.com/paper/1809.00219/) (2018)
- [EfficientDet: Scalable and Efficient Object Detection](https://mlsanity.com/paper/1911.09070/) (2019)
- [Toward Real-World Single Image Super-Resolution: A New Benchmark and A New Model](https://mlsanity.com/paper/1904.00523/) (2019)
- [Deep Unfolding Network for Image Super-Resolution](https://mlsanity.com/paper/2003.10428/) (2020)
- [Component Divide-and-Conquer for Real-World Image Super-Resolution](https://mlsanity.com/paper/2008.01928/) (2020)
- [Contrastive Learning for Compact Single Image Dehazing](https://mlsanity.com/paper/2104.09367/) (2021)
- [Blind Super-Resolution With Iterative Kernel Correction](https://mlsanity.com/paper/1904.03377/) (2019)
- [Unsupervised Intra-domain Adaptation for Semantic Segmentation through Self-Supervision](https://mlsanity.com/paper/2004.07703/) (2020)
- [Unsupervised Degradation Representation Learning for Blind Super-Resolution](https://mlsanity.com/paper/2104.00416/) (2021)
- [Blind Super-Resolution Kernel Estimation using an Internal-GAN](https://mlsanity.com/paper/1909.06581/) (2019)
- [Unfolding the Alternating Optimization for Blind Super Resolution](https://mlsanity.com/paper/2010.02631/) (2020)
- [Blind Image Super-Resolution: A Survey and Beyond](https://mlsanity.com/paper/2107.03055/) (2021)
- [Flow-based Kernel Prior with Application to Blind Super-Resolution](https://mlsanity.com/paper/2103.15977/) (2021)
- [Training GANs with Stronger Augmentations via Contrastive Discriminator](https://mlsanity.com/paper/2103.09742/) (2021)
- [ShuffleMixer: An Efficient ConvNet for Image Super-Resolution](https://mlsanity.com/paper/2205.15175/) (2022)
- [Channel-wise and Spatial Feature Modulation Network for Single Image Super-Resolution](https://mlsanity.com/paper/1809.11130/) (2018)
- [KOALAnet: Blind Super-Resolution using Kernel-Oriented Adaptive Local Adjustment](https://mlsanity.com/paper/2012.08103/) (2020)
- [Blind Image Super-Resolution via Contrastive Representation Learning](https://mlsanity.com/paper/2107.00708/) (2021)
- [A Practical Contrastive Learning Framework for Single-Image Super-Resolution](https://mlsanity.com/paper/2111.13924/) (2021)
- [Memory-augmented Deep Unfolding Network for Guided Image Super-resolution](https://mlsanity.com/paper/2203.04960/) (2022)
- [Towards Compact Single Image Super-Resolution via Contrastive Self-distillation](https://mlsanity.com/paper/2105.11683/) (2021)
- [CDPMSR: Conditional Diffusion Probabilistic Models for Single Image Super-Resolution](https://mlsanity.com/paper/2302.12831/) (2023)

## Built on by (most cited first, 9 of 9)

- [Efficient Real-world Image Super-Resolution Via Adaptive Directional Gradient Convolution](https://mlsanity.com/paper/2405.07023/) (2024)
- [ACDMSR: Accelerated Conditional Diffusion Models for Single Image Super-Resolution](https://mlsanity.com/paper/2307.00781/) (2023)
- [Diff-Restorer: Unleashing Visual Prompts for Diffusion-based Universal Image Restoration](https://mlsanity.com/paper/2407.03636/) (2024)
- [Cross-view Masked Diffusion Transformers for Person Image Synthesis](https://mlsanity.com/paper/2402.01516/) (2024)
- [MDSGen: Fast and Efficient Masked Diffusion Temporal-Aware Transformers for Open-Domain Sound Generation](https://mlsanity.com/paper/2410.02130/) (2024)
- [RealOSR: Latent Guidance Boosts Diffusion-based Real-world Omnidirectional Image Super-Resolutions](https://mlsanity.com/paper/2412.09646/) (2024)
- [E-MD3C: Taming Masked Diffusion Transformers for Efficient Zero-Shot Object Customization](https://mlsanity.com/paper/2502.09164/) (2025)
- [DifAugGAN: A Practical Diffusion-style Data Augmentation for GAN-based Single Image Super-resolution](https://mlsanity.com/paper/2311.18508/) (2023)
- [Unsupervised Image Super-Resolution Reconstruction Based on Real-World Degradation Patterns](https://mlsanity.com/paper/2506.17027/) (2025)

## Abstract (arXiv)

Currently, there are two popular approaches for addressing real-world image super-resolution problems: degradation-estimation-based and blind-based methods. However, degradation-estimation-based methods may be inaccurate in estimating the degradation, making them less applicable to real-world LR images. On the other hand, blind-based methods are often limited by their fixed single perception information, which hinders their ability to handle diverse perceptual characteristics. To overcome this limitation, we propose a novel SR method called MPF-Net that leverages multiple perceptual features of input images. Our method incorporates a Multi-Perception Feature Extraction (MPFE) module to extract diverse perceptual information and a series of newly-designed Cross-Perception Blocks (CPB) to combine this information for effective super-resolution reconstruction. Additionally, we introduce a contrastive regularization term (CR) that improves the model's learning capability by using newly generated HR and LR images as positive and negative samples for ground truth HR. Experimental results on challenging real-world SR datasets demonstrate that our approach significantly outperforms existing state-of-the-art methods in both qualitative and quantitative measures.