图像复原
计算机科学
计算机视觉
图像处理
相位调制
物理
人工智能
信号处理
频率调制
调制(音乐)
光学滤波器
图像(数学)
噪音(视频)
算法
数学
光学
信噪比(成像)
迭代重建
控制理论(社会学)
杂乱
相位噪声
降级(电信)
合成孔径雷达
图像压缩
脉冲宽度调制
作者
Shihao Zhao,Wanglong Lu,Binhao Wang,Tao Wang,Kaihao Zhang,Hanli Zhao
标识
DOI:10.1109/tcsvt.2026.3707458
摘要
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 multi-scale 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 athttps://github.com/Zhao0100/UHDRes
科研通智能强力驱动
Strongly Powered by AbleSci AI