用频谱调和实现高效一体化天气修复，参数少80%却保持高质量。
Efficient All-in-One Weather Restoration using Spectral Harmonization
- 通过傅里叶分解在多尺度架构中分离高低频特征。
- 相比基于Transformer模型，参数与运算量减少80%仍保持相似效果。
- 适合资源受限设备，如移动端或嵌入式系统部署。
雨、雾、雪等恶劣天气会严重降低图像质量，对人眼感知和物理人工智能都带来挑战。现有修复方法计算开销大，难以处理高分辨率图像且无法统一应对多种退化。本文提出频谱调和重建（FReSH-IR），一种轻量级一体化修复方法，在分层编码器-解码器架构中显式地将特征表示按尺度分解为高低频成分。通过傅里叶基跳跃连接结合频谱分解与空间处理，该方法在不损失空间细节的前提下捕获互补频率信息。实验表明，本方法在参数和运算量上比基于Transformer的模型减少80%，同时达到相近的修复质量。大量实验验证了其在性能与效率间的优异平衡，凸显其在资源受限系统中的实际应用潜力。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。