Ultra-High-Definition Restoration Transformers with Correlation Matching Transformation

• URL: http://arxiv.org/abs/2608.20263v1
• Date: Tue, 18 Aug 2026 20:41:27 GMT
• Title: Ultra-High-Definition Restoration Transformers with Correlation Matching Transformation
• Abstract summary: UHDformer++ is a Transformer-based framework to solve Ultra-High-Definition (UHD) image restoration tasks.<n>It operates across four learning spaces: 1) a high-resolution space (HR) for multi-level feature extraction, 2) a low-resolution space (LR) for learning compact, representative features, 3) a super-resolution space (SR) for up low-resolution features from SR, and 4) a low-high fusion and reconstruction space (LHFR) for final image restoration.
• Score: 113.23094779244771
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We propose UHDformer++, a general Transformer-based framework to solve numerous Ultra-High-Definition (UHD) image restoration tasks. UHDformer++ operates across $4$ coordinated learning spaces: 1) a high-resolution space (HR) for multi-level feature extraction, 2) a low-resolution space (LR) for learning compact, representative features, 3) a super-resolution space (SR) for upsampling low-resolution features from SR, and 4) a low-high fusion and reconstruction space (LHFR) for final image restoration. Specifically, HR extracts multi-scale high-resolution features and fuses them with low-resolution cues to produce residual images, while LR distills complementary representations from HR to improve restoration quality. To supply LHFR with richer features, SR super-resolves LR outputs before fusion. We further introduce two modules to bridge the high- and low-resolution spaces. The Feature-Refined Correlation Matching Transformation (FR-CMT) module selects the top $C/r~(C~\text{denotes the number of channels;~}r\geq1~\text{controls the squeezing level})$, from the fusion between max- and mean-pooled high-resolution features to replace less informative channels in the low-resolution Transformer. The Adaptive Channel Modulator (ACM) adaptively recalibrates multi-scale high-resolution features, ensuring that only task-relevant information propagates to LR. Extensive experiments demonstrate that UHDformer++ reduces model parameters by at least 86\% compared with recent state-of-the-art methods while achieving substantial performance gains across $5$ UHD restoration tasks, including low-light image enhancement, dehazing, deblurring, deraining, and desnowing. Code will be released at https://github.com/supersupercong/uhdformerplus.

Related papers

• Pixel to Gaussian: Ultra-Fast Continuous Super-Resolution with 2D Gaussian Modeling [50.34513854725803]
  Arbitrary-scale super-resolution (ASSR) aims to reconstruct high-resolution (HR) images from low-resolution (LR) inputs with arbitrary upsampling factors.<n>We propose a novel ContinuousSR framework with a Pixel-to-Gaussian paradigm, which explicitly reconstructs 2D continuous HR signals from LR images using Gaussian Splatting.
  arXiv  Detail & Related papers  (2025-03-09T13:43:57Z)
• Correlation Matching Transformation Transformers for UHD Image Restoration [46.569124456928535]
  This paper proposes 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. Experiments show that our UHDformer reduces about ninety-seven percent model sizes compared with most state-of-the-art methods.
  arXiv  Detail & Related papers  (2024-06-02T06:10:48Z)
• Latent Modulated Function for Computational Optimal Continuous Image Representation [20.678662838709542]
  We propose a novel Latent Modulated Rendering (LMF) algorithm for continuous image representation. We show that converting existing INR-based methods to LMF can reduce the computational cost by up to 99.9%. Experiments demonstrate that converting existing INR-based methods to LMF can reduce inference by up to 57 times, and save up to 76% parameters.
  arXiv  Detail & Related papers  (2024-04-25T09:30:38Z)
• DCS-RISR: Dynamic Channel Splitting for Efficient Real-world Image Super-Resolution [15.694407977871341]
  Real-world image super-resolution (RISR) has received increased focus for improving the quality of SR images under unknown complex degradation. Existing methods rely on the heavy SR models to enhance low-resolution (LR) images of different degradation levels. We propose a novel Dynamic Channel Splitting scheme for efficient Real-world Image Super-Resolution, termed DCS-RISR.
  arXiv  Detail & Related papers  (2022-12-15T04:34:57Z)
• Reference-based Image Super-Resolution with Deformable Attention Transformer [62.71769634254654]
  RefSR aims to exploit auxiliary reference (Ref) images to super-resolve low-resolution (LR) images. This paper proposes a deformable attention Transformer, namely DATSR, with multiple scales. Experiments demonstrate that our DATSR achieves state-of-the-art performance on benchmark datasets.
  arXiv  Detail & Related papers  (2022-07-25T07:07:00Z)
• Towards Lightweight Super-Resolution with Dual Regression Learning [58.98801753555746]
  Deep neural networks have exhibited remarkable performance in image super-resolution (SR) tasks. The SR problem is typically an ill-posed problem and existing methods would come with several limitations. We propose a dual regression learning scheme to reduce the space of possible SR mappings.
  arXiv  Detail & Related papers  (2022-07-16T12:46:10Z)
• LAPAR: Linearly-Assembled Pixel-Adaptive Regression Network for Single Image Super-Resolution and Beyond [75.37541439447314]
  Single image super-resolution (SISR) deals with a fundamental problem of upsampling a low-resolution (LR) image to its high-resolution (HR) version. This paper proposes a linearly-assembled pixel-adaptive regression network (LAPAR) to strike a sweet spot of deep model complexity and resulting SISR quality.
  arXiv  Detail & Related papers  (2021-05-21T15:47:18Z)
• Super-Resolution of Real-World Faces [3.4376560669160394]
  Real low-resolution (LR) face images contain degradations which are too varied and complex to be captured by known downsampling kernels. In this paper, we propose a two module super-resolution network where the feature extractor module extracts robust features from the LR image. We train a degradation GAN to convert bicubically downsampled clean images to real degraded images, and interpolate between the obtained degraded LR image and its clean LR counterpart.
  arXiv  Detail & Related papers  (2020-11-04T17:25:54Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.