发表机构
Cidaut AI; Fundación Cidaut; Technical University of Munich（Cidaut AI; Cidaut基金会; 慕尼黑工业大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出轻量级一体化天气复原方法FReSH-IR，通过光谱协调分解特征频率，参数与运算量较Transformer模型减少80%，实现高效性能权衡，适配资源受限系统。
AI 中文摘要
雨、霾、雪等恶劣天气条件会严重降低图像质量，对人类感知和物理AI均构成挑战。现有复原方法需要大量计算资源，难以处理高分辨率图像并应对不同类型的退化。本文提出一种名为FReSH-IR的新型轻量级一体化复原方法，即通过光谱协调实现频率重构，该方法在分层编解码器架构的每个尺度上将特征表示显式分解为高频和低频分量。通过基于傅里叶的跳跃连接将光谱分解与空间处理相结合，FReSH-IR可在不损失空间细节的情况下捕获互补频率信息。与基于Transformer的模型相比，该方法实现了相近的复原质量，但参数和运算量减少了80%。大量实验表明，该方法实现了出色的效率-性能权衡，凸显了其在资源受限系统中的实际应用价值。
英文摘要
Adverse weather conditions such as rain, haze, and snow significantly degrade image quality, posing challenges for both human perception and physical AI. Existing restoration methods require large computational budgets, struggling to process high-resolution images and handle different degradations. In this paper, we present Frequency Reconstruction via Spectral Harmonization, a novel lightweight all-in-one restoration method that explicitly decomposes feature representations into high- and low-frequency components at each scale of a hierarchical encoder-decoder architecture. By combining spectral decomposition with spatial processing through Fourier-based skip connections, FReSH-IR captures complementary frequency information without sacrificing spatial detail. Our approach achieves similar restoration quality with 80% fewer parameters and operations than transformer-based models. Extensive experiments demonstrate that our method offers a great efficiency-performance trade-off, highlighting its practical applications in constrained-resource systems.
CommentsTechnical Report
