Salvato in:
| Autori principali: | , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2604.15654 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866908973497581568 |
|---|---|
| author | Zhao, Chen Xu, Yunzhe Chen, Zhizhou Gu, Enxuan Zhang, Kai Liu, Xiaoming Yang, Jian Tai, Ying |
| author_facet | Zhao, Chen Xu, Yunzhe Chen, Zhizhou Gu, Enxuan Zhang, Kai Liu, Xiaoming Yang, Jian Tai, Ying |
| contents | 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 \textbf{enhancement}, low-frequency \textbf{restoration}, and high-frequency \textbf{refinement}. Based on this formulation, we propose a novel framework, \textbf{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, \textbf{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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_15654 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | From Zero to Detail: A Progressive Spectral Decoupling Paradigm for UHD Image Restoration with New Benchmark Zhao, Chen Xu, Yunzhe Chen, Zhizhou Gu, Enxuan Zhang, Kai Liu, Xiaoming Yang, Jian Tai, Ying Computer Vision and Pattern Recognition 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 \textbf{enhancement}, low-frequency \textbf{restoration}, and high-frequency \textbf{refinement}. Based on this formulation, we propose a novel framework, \textbf{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, \textbf{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. |
| title | From Zero to Detail: A Progressive Spectral Decoupling Paradigm for UHD Image Restoration with New Benchmark |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2604.15654 |