UHDRes: Ultra-High-Definition Image Restoration via Dual-Domain Decoupled Spectral Modulation
This addresses image restoration for high-resolution UHD images, offering a computationally efficient solution for applications requiring real-time processing.
The paper tackles the problem of restoring ultra-high-definition images from degradations like blur and haze by proposing UHDRes, a lightweight dual-domain framework that achieves state-of-the-art performance with only 400K parameters, reducing inference latency and memory usage.
Ultra-high-definition (UHD) images often suffer from severe degradations such as blur, haze, rain, or low-light conditions, which pose significant challenges for image restoration due to their high resolution and computational demands. In this paper, we propose UHDRes, a novel lightweight dual-domain decoupled spectral modulation framework for UHD image restoration. It explicitly models the amplitude spectrum via lightweight spectrum-domain modulation, while restoring phase implicitly through spatial-domain refinement. We introduce the spatio-spectral fusion mechanism, which first employs a multi-scale context aggregator to extract local and global spatial features, and then performs spectral modulation in a decoupled manner. It explicitly enhances amplitude features in the frequency domain while implicitly restoring phase information through spatial refinement. Additionally, a shared gated feed-forward network is designed to efficiently promote feature interaction through shared-parameter convolutions and adaptive gating mechanisms. Extensive experimental comparisons on five public UHD benchmarks demonstrate that our UHDRes achieves the state-of-the-art restoration performance with only 400K parameters, while significantly reducing inference latency and memory usage. The codes and models are available at https://github.com/Zhao0100/UHDRes.