From Zero to Detail: A Progressive Spectral Decoupling Paradigm for UHD Image Restoration with New Benchmark
Not on the map. Why?
Abstract (arXiv)
Ultra-high-definition (UHD) image restoration poses unique challenges due to the high spatial resolution, diverse content, and fine-grained structures present in UHD images. To address these issues, we introduce a progressive spectral decomposition for the restoration process, decomposing it into three stages: zero-frequency enhancement, low-frequency restoration, and high-frequency refinement. Based on this formulation, we propose a novel framework, ERR, which integrates three cooperative sub-networks: the zero-frequency enhancer (ZFE), the low-frequency restorer (LFR), and the high-frequency refiner (HFR). The ZFE incorporates global priors to learn holistic mappings, the LFR reconstructs the main content by focusing on coarse-scale information, and the HFR adopts our proposed frequency-windowed Kolmogorov-Arnold Network (FW-KAN) to recover fine textures and intricate details for high-fidelity restoration. To further advance research in UHD image restoration, we also construct a large-scale, high-quality benchmark dataset, LSUHDIR, comprising 82,126 UHD images with diverse scenes and rich content. Our proposed methods demonstrate superior performance across a range of UHD image restoration tasks, and extensive ablation studies confirm the contribution and necessity of each module. Project page: https://github.com/NJU-PCALab/ERR.
Key facts. Cited by 7 papers in the map (data through 14 Oct 2026). Builds on 89 of its 130 references that are in the map. First posted on arXiv 17 Apr 2026.
Builds on
89 of 130 references.
References · 89
- 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
- 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 5,045
- 2021SwinIR: Image Restoration Using Swin Transformercited by 1,887
- 2021Restormer: Efficient Transformer for High-Resolution Image Restorationcited by 1,627
- 2016Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoisingcited by 1,358
- 2014Image Super-Resolution Using Deep Convolutional Networkscited by 1,224
- 2021Uformer: A General U-Shaped Transformer for Image Restorationcited by 866
- 2021Multi-Stage Progressive Image Restorationcited by 816
- 2021Resolution-robust Large Mask Inpainting with Fourier Convolutionscited by 738
- 2018Deep Retinex Decomposition for Low-Light Enhancementcited by 723
- 2022Simple Baselines for Image Restorationcited by 708
- 2024KAN: Kolmogorov-Arnold Networkscited by 649
38 more
- 2019Toward Real-World Single Image Super-Resolution: A New Benchmark and A New Modelcited by 403
- 2024MambaIR: A Simple Baseline for Image Restoration with State-Space Modelcited by 352
- 2019FFA-Net: Feature Fusion Attention Network for Single Image Dehazingcited by 307
- 2024MACE: Mass Concept Erasure in Diffusion Modelscited by 307
- 2020Multi-Scale Progressive Fusion Network for Single Image Derainingcited by 260
- 2022Vision Transformers for Single Image Dehazingcited by 260
- 2019An Underwater Image Enhancement Benchmark Dataset and Beyondcited by 253
- 2023Retinexformer: One-stage Retinex-based Transformer for Low-light Image Enhancementcited by 231
- 2020Multi-Scale Boosted Dehazing Network with Dense Feature Fusioncited by 230
- 2023Learning A Sparse Transformer Network for Effective Image Derainingcited by 205
- 2023TF-ICON: Diffusion-Based Training-Free Cross-Domain Image Compositioncited by 182
- 2020FcaNet: Frequency Channel Attention Networkscited by 179
- 2022Ultra-High-Definition Low-Light Image Enhancement: A Benchmark and Transformer-Based Methodcited by 174
- 2022Efficient Frequency Domain-based Transformers for High-Quality Image Deblurringcited by 165
- 2023Efficient and Explicit Modelling of Image Hierarchies for Image Restorationcited by 145
- 2023Low-Light Image Enhancement with Wavelet-based Diffusion Modelscited by 127
- 2024MIGC: Multi-Instance Generation Controller for Text-to-Image Synthesiscited by 124
- 2019Frequency Separation for Real-World Super-Resolutioncited by 115
- 2021U-shape Transformer for Underwater Image Enhancementcited by 112
- 2024Robust Watermarking Using Generative Priors Against Image Editing: From Benchmarking to Advancescited by 110
- 2020NH-HAZE: An Image Dehazing Benchmark with Non-Homogeneous Hazy and Haze-Free Imagescited by 108
- 2019Dense Haze: A benchmark for image dehazing with dense-haze and haze-free imagescited by 107
- 2022LEDNet: Joint Low-light Enhancement and Deblurring in the Darkcited by 96
- 2018O-HAZE: a dehazing benchmark with real hazy and haze-free outdoor imagescited by 95
- 2024EraseAnything: Enabling Concept Erasure in Rectified Flow Transformerscited by 95
- 2023Wavelet-based Fourier Information Interaction with Frequency Diffusion Adjustment for Underwater Image Restorationcited by 88
- 2023Embedding Fourier for Ultra-High-Definition Low-Light Image Enhancementcited by 86
- 2023Curricular Contrastive Regularization for Physics-aware Single Image Dehazingcited by 83
- 2021Intriguing Findings of Frequency Selection for Image Deblurringcited by 81
- 2023MB-TaylorFormer: Multi-branch Efficient Transformer Expanded by Taylor Formula for Image Dehazingcited by 81
- 2023Pyramid Diffusion Models For Low-light Image Enhancementcited by 67
- 2024AddSR: Accelerating Diffusion-based Blind Super-Resolution with Adversarial Diffusion Distillationcited by 66
- 2021Structure-Preserving Deraining with Residue Channel Prior Guidancecited by 63
- 2025HVI: A New Color Space for Low-light Image Enhancementcited by 63
- 2025Set You Straight: Auto-Steering Denoising Trajectories to Sidestep Unwanted Conceptscited by 62
- 2024Exploiting Multimodal Spatial-temporal Patterns for Video Object Trackingcited by 57
- 2024Kolmogorov-Arnold Transformercited by 56
- 2015Seven ways to improve example-based single image super resolutioncited by 51
50 most cited of 89 All 89 (JSON)
Built on by
Citing papers per year: 2026: 7.
7 papers.
- 2026L2P: Unlocking Latent Potential for Pixel Generationcited by 9
- 2026MetaPoint: Unlocking Precise Spatial Control in Agentic Visual Generationcited by 4
- 2026Learning to Refine: Spectral-Decoupled Iterative Refinement Framework for Precipitation Nowcastingcited by 3
- 2026Temporal and Cross-Modal Alignment for Enhanced Audiovisual Video Captioningcited by 3
- 2026Spiking Pyramid Wavelet Transformation for High-efficient and Low-energy Image Restorationcited by 2
- 2026SynVAR: Synergizing Spatial and Semantic Alignment in Visual Autoregressive Modelcited by 0
- 2026Structured Stateful Relational Scripts with a High-Quality Dataset for Multi-Shot Audio-Visual Video Generationcited by 0
- 2026Structured Stateful Relational Scripts with a High-Quality Dataset for Multi-Shot Audio-Visual Video Generation11 Oct 2026
- 2026SynVAR: Synergizing Spatial and Semantic Alignment in Visual Autoregressive Model8 Aug 2026
- 2026Temporal and Cross-Modal Alignment for Enhanced Audiovisual Video Captioning2 Jul 2026
- 2026Spiking Pyramid Wavelet Transformation for High-efficient and Low-energy Image Restoration17 Jun 2026
- 2026MetaPoint: Unlocking Precise Spatial Control in Agentic Visual Generation3 Jun 2026
- 2026Learning to Refine: Spectral-Decoupled Iterative Refinement Framework for Precipitation Nowcasting1 Jun 2026
- 2026L2P: Unlocking Latent Potential for Pixel Generation12 May 2026