Pixel Ignores, Superpixel Sees: Adverse Weather Image Restoration via Semantic-Center SSM

2026-08-03

AI Summary

This work addresses the semantic inconsistency arising in image restoration under complex weather conditions due to pixel-level modeling that neglects spatial non-uniformity. To this end, we propose a Semantic-center-guided State Space Restoration model (SSR), which introduces two novel components: a Superpixel-guided Selective Scanning Mechanism (S³M) and a Region-wise Gating Mechanism (RGM). These innovations shift the conventional serial pixel-wise scanning paradigm to a semantics-aware scanning strategy guided by semantically coherent superpixels. Within each region, the model explicitly captures degradation correlations and calibrates outliers, enabling high-fidelity, semantics-preserving restoration. Extensive experiments on six mainstream benchmarks demonstrate that SSR consistently outperforms existing methods, achieving superior performance with controlled computational overhead.

Abstract

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.

Problem

• adverse weather image restoration
• spatially non-uniform degradation
• semantic-conflict regions
• image dehazing
• weather-related degradation

Innovation

• Semantic-guided scanning
• Superpixel clustering
• State space model
• Adverse weather restoration
• Region-level gating