From Zero to Detail: A Progressive Spectral Decoupling Paradigm for UHD Image Restoration with New Benchmark

TL;DR

This paper introduces a progressive spectral decomposition framework for UHD image restoration, utilizing three cooperative sub-networks and a new benchmark dataset to achieve high-fidelity results.

Contribution

It proposes a novel ERR framework with spectral decomposition stages and a new large-scale UHD image dataset for improved restoration performance.

Findings

ERR outperforms existing methods on UHD restoration tasks.

The frequency-windowed Kolmogorov-Arnold Network effectively recovers fine details.

A comprehensive benchmark dataset supports future research.

Abstract

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.