发表机构
Nankai International Advanced Research Institute; Peng Cheng Laboratory; College of Computer Science, Nankai University; University of Science and Technology Beijing; University of Macau（南开大学国际高等研究院; 鹏城实验室; 南开大学计算机学院; 北京科技大学; 澳门大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究针对现有恶劣天气图像修复模型的缺陷，提出SSR模型，通过S³M与RGM机制实现更优修复性能，在6个基准上优于现有模型且计算成本有竞争力。
AI 中文摘要
恶劣天气图像修复旨在从复杂天气条件下的降质图像中恢复清晰可见度。现有研究尝试通过建模像素间关系解决该问题，但该范式违背了降质的空间非均匀性事实，且会从语义冲突区域学习到无判别性特征。本文提出用于图像修复的语义中心引导状态空间模型（Semantic-center guilded State space model, SSR），其核心思想是将传统的像素串行扫描策略转变为语义引导策略。具体而言，本文引入超像素引导选择性扫描机制（Superpixel-guided Selective Scan Mechanism, S³M），该机制首先通过超像素聚类将图像划分为感知一致的区域，随后在语义相关区域内进行关系建模；此外，本文还提出区域级门控机制（Region-level Gating Mechanism, RGM），用于在每个语义超像素单元内沿通道维度调制降质异常值，以实现区域内校准。在6个成熟基准上开展的大量实验表明，SSR模型在具有竞争力的计算成本下，性能优于现有最先进的模型。
英文摘要
Adverse weather image restoration aims to recover clear visibility from degraded images in complex weather conditions. Existing works attempt to address this problem by modeling relationships between pixels, however, this paradigm defies the spatially non-uniformity fact of degradations and learns non-discriminative features from semantic-conflict regions. In this paper, we propose SSR, a \textbf{S}emantic-center guilded \textbf{S}tate space model for image \textbf{R}estoration. The key idea of SSR is to shift the conventional scanning strategy of pixel-serial to semantic-guilded one. Specifically, we introduce a Superpixel-guided Selective Scan Mechanism ($\text{S}^3$M), which first partitions the image into perceptually coherent regions via superpixel clustering and then performs relations modeling within the semantic-related regions. Moreover, a Region-level Gating Mechanism (RGM) is developed to perform intra-region calibration by modulating degradation outliers within each semantic superpixel unit along the channel dimension. Extensive experiments on \textbf{6} well-established benchmarks demonstrate that SSR performs favorably against state-of-the-art models with competitive computational cost.
