# Correlation Matching Transformation Transformers for UHD Image Restoration

arXiv: https://arxiv.org/abs/2406.00629 · HTML: https://mlsanity.com/paper/2406.00629/

## Key facts

- Cited by 39 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 34 references that are in the map.
- First posted on arXiv 2 Jun 2024.

## Builds on (most cited first, 20 of 20)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [SwinIR: Image Restoration Using Swin Transformer](https://mlsanity.com/paper/2108.10257/) (2021)
- [Restormer: Efficient Transformer for High-Resolution Image Restoration](https://mlsanity.com/paper/2111.09881/) (2021)
- [Multi-Stage Progressive Image Restoration](https://mlsanity.com/paper/2102.02808/) (2021)
- [Deep Multi-scale Convolutional Neural Network for Dynamic Scene Deblurring](https://mlsanity.com/paper/1612.02177/) (2016)
- [Deep Retinex Decomposition for Low-Light Enhancement](https://mlsanity.com/paper/1808.04560/) (2018)
- [ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks](https://mlsanity.com/paper/1910.03151/) (2019)
- [Benchmarking Single Image Dehazing and Beyond](https://mlsanity.com/paper/1712.04143/) (2017)
- [Rethinking Coarse-to-Fine Approach in Single Image Deblurring](https://mlsanity.com/paper/2108.05054/) (2021)
- [Vision-Language Transformer and Query Generation for Referring Segmentation](https://mlsanity.com/paper/2108.05565/) (2021)
- [Multi-Scale Boosted Dehazing Network with Dense Feature Fusion](https://mlsanity.com/paper/2004.13388/) (2020)
- [GridDehazeNet: Attention-Based Multi-Scale Network for Image Dehazing](https://mlsanity.com/paper/1908.03245/) (2019)
- [Deep Stacked Hierarchical Multi-patch Network for Image Deblurring](https://mlsanity.com/paper/1904.03468/) (2019)
- [Efficient Frequency Domain-based Transformers for High-Quality Image Deblurring](https://mlsanity.com/paper/2211.12250/) (2022)
- [Unsupervised Night Image Enhancement: When Layer Decomposition Meets Light-Effects Suppression](https://mlsanity.com/paper/2207.10564/) (2022)
- [DCSFN: Deep Cross-scale Fusion Network for Single Image Rain Removal](https://mlsanity.com/paper/2008.00767/) (2020)
- [Enhancing Visibility in Nighttime Haze Images Using Guided APSF and Gradient Adaptive Convolution](https://mlsanity.com/paper/2308.01738/) (2023)
- [Structure Representation Network and Uncertainty Feedback Learning for Dense Non-Uniform Fog Removal](https://mlsanity.com/paper/2210.03061/) (2022)

## Built on by (most cited first, 30 of 39)

- [Wave-Mamba: Wavelet State Space Model for Ultra-High-Definition Low-Light Image Enhancement](https://mlsanity.com/paper/2408.01276/) (2024)
- [From Zero to Detail: Deconstructing Ultra-High-Definition Image Restoration from Progressive Spectral Perspective](https://mlsanity.com/paper/2503.13165/) (2025)
- [Dropout the High-rate Downsampling: A Novel Design Paradigm for UHD Image Restoration](https://mlsanity.com/paper/2411.06456/) (2024)
- [Raindrop Clarity: A Dual-Focused Dataset for Day and Night Raindrop Removal](https://mlsanity.com/paper/2407.16957/) (2024)
- [Ultra-High-Definition Image Restoration: New Benchmarks and A Dual Interaction Prior-Driven Solution](https://mlsanity.com/paper/2406.13607/) (2024)
- [MobileIE: An Extremely Lightweight and Effective ConvNet for Real-Time Image Enhancement on Mobile Devices](https://mlsanity.com/paper/2507.01838/) (2025)
- [CWNet: Causal Wavelet Network for Low-Light Image Enhancement](https://mlsanity.com/paper/2507.10689/) (2025)
- [Scan Clusters, Not Pixels: A Cluster-Centric Paradigm for Efficient Ultra-high-definition Image Restoration](https://mlsanity.com/paper/2602.21917/) (2026)
- [Neural Discrimination-Prompted Transformers for Efficient UHD Image Restoration and Enhancement](https://mlsanity.com/paper/2603.00853/) (2026)
- [From Zero to Detail: A Progressive Spectral Decoupling Paradigm for UHD Image Restoration with New Benchmark](https://mlsanity.com/paper/2604.15654/) (2026)
- [Deep Learning-Driven Ultra-High-Definition Image Restoration: A Survey](https://mlsanity.com/paper/2505.16161/) (2025)
- [Ultra-High-Definition Dynamic Multi-Exposure Image Fusion via Infinite Pixel Learning](https://mlsanity.com/paper/2412.11685/) (2024)
- [SPJFNet: Self-Mining Prior-Guided Joint Frequency Enhancement for Ultra-Efficient Dark Image Restoration](https://mlsanity.com/paper/2508.04041/) (2025)
- [RetinexDual: Retinex-based Dual Nature Approach for Generalized Ultra-High-Definition Image Restoration](https://mlsanity.com/paper/2508.04797/) (2025)
- [Latent Harmony: Synergistic Unified UHD Image Restoration via Latent Space Regularization and Controllable Refinement](https://mlsanity.com/paper/2510.07961/) (2025)
- [Decouple to Reconstruct: High Quality UHD Restoration via Active Feature Disentanglement and Reversible Fusion](https://mlsanity.com/paper/2503.12764/) (2025)
- [Adapting Large VLMs with Iterative and Manual Instructions for Generative Low-light Enhancement](https://mlsanity.com/paper/2507.18064/) (2025)
- [DRWKV: Focusing on Object Edges for Low-Light Image Enhancement](https://mlsanity.com/paper/2507.18594/) (2025)
- [RetinexDualV2: Physically-Grounded Dual Retinex for Generalized UHD Image Restoration](https://mlsanity.com/paper/2603.27979/) (2026)
- [LiBrA-Net: Lie-Algebraic Bilateral Affine Fields for Real-Time 4K Video Dehazing](https://mlsanity.com/paper/2605.11508/) (2026)
- [PixRestore: Unified Image Restoration via Pixel Diffusion Transformer](https://mlsanity.com/paper/2608.16793/) (2026)
- [TSFormer: A Robust Framework for Efficient UHD Image Restoration](https://mlsanity.com/paper/2411.10951/) (2024)
- [UHD Image Dehazing via anDehazeFormer with Atmospheric-aware KV Cache](https://mlsanity.com/paper/2505.14010/) (2025)
- [BSMamba: Brightness and Semantic Modeling for Long-Range Interaction in Low-Light Image Enhancement](https://mlsanity.com/paper/2506.18346/) (2025)
- [Beyond Illumination: Fine-Grained Detail Preservation in Extreme Dark Image Restoration](https://mlsanity.com/paper/2508.03336/) (2025)
- [Towards Perfection: Building Inter-component Mutual Correction for Retinex-based Low-light Image Enhancement](https://mlsanity.com/paper/2508.09009/) (2025)
- [UHDRes: Ultra-High-Definition Image Restoration via Dual-Domain Decoupled Spectral Modulation](https://mlsanity.com/paper/2511.05009/) (2025)
- [Degradation-Aware Prompt Learning with Cross-Modal Compensation for Adverse Weather Removal](https://mlsanity.com/paper/2608.06939/) (2026)
- [Uncertainty-Aware Spatial Color Correlation for Low-Light Image Enhancement](https://mlsanity.com/paper/2508.04176/) (2025)
- [RED: Robust Event-Guided Motion Deblurring with Modality-Specific Disentanglement](https://mlsanity.com/paper/2509.05554/) (2025)

## Abstract (arXiv)

This paper proposes UHDformer, a general Transformer for Ultra-High-Definition (UHD) image restoration. UHDformer contains two learning spaces: (a) learning in high-resolution space and (b) learning in low-resolution space. The former learns multi-level high-resolution features and fuses low-high features and reconstructs the residual images, while the latter explores more representative features learning from the high-resolution ones to facilitate better restoration. To better improve feature representation in low-resolution space, we propose to build feature transformation from the high-resolution space to the low-resolution one. To that end, we propose two new modules: Dual-path Correlation Matching Transformation module (DualCMT) and Adaptive Channel Modulator (ACM). The DualCMT selects top C/r (r is greater or equal to 1 which controls the squeezing level) correlation channels from the max-pooling/mean-pooling high-resolution features to replace low-resolution ones in Transformers, which can effectively squeeze useless content to improve the feature representation in low-resolution space to facilitate better recovery. The ACM is exploited to adaptively modulate multi-level high-resolution features, enabling to provide more useful features to low-resolution space for better learning. Experimental results show that our UHDformer reduces about ninety-seven percent model sizes compared with most state-of-the-art methods while significantly improving performance under different training sets on 3 UHD image restoration tasks, including low-light image enhancement, image dehazing, and image deblurring. The source codes will be made available at https://github.com/supersupercong/UHDformer.