MODEM: A Morton-Order Degradation Estimation Mechanism for Adverse Weather Image Recovery

2025-05-23

AI Summary

To address the challenge of modeling highly non-uniform and spatially heterogeneous image degradation under adverse weather conditions, this paper proposes a Morton-order-based degradation estimation framework. Methodologically, we introduce the Morton-Order 2D Selective Scanning (MOS2D) module—the first to integrate space-filling curve encoding with selective state-space models (SSMs), enabling unified long-range dependency modeling and local structural preservation. Additionally, we design a Dual Degradation Estimation Module (DDEM) that decouples global and local degradation priors and achieves adaptive restoration via dynamic conditional modulation. Extensive experiments across multiple weather types—including rain, fog, and snow—and diverse benchmark datasets demonstrate state-of-the-art performance. Our approach significantly improves detail fidelity and structural consistency in restored images.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Machine Learning: Multimodal Learning
• Intelligent Robots: State Estimation

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs

Abstract

Restoring images degraded by adverse weather remains a significant challenge due to the highly non-uniform and spatially heterogeneous nature of weather-induced artifacts, e.g., fine-grained rain streaks versus widespread haze. Accurately estimating the underlying degradation can intuitively provide restoration models with more targeted and effective guidance, enabling adaptive processing strategies. To this end, we propose a Morton-Order Degradation Estimation Mechanism (MODEM) for adverse weather image restoration. Central to MODEM is the Morton-Order 2D-Selective-Scan Module (MOS2D), which integrates Morton-coded spatial ordering with selective state-space models to capture long-range dependencies while preserving local structural coherence. Complementing MOS2D, we introduce a Dual Degradation Estimation Module (DDEM) that disentangles and estimates both global and local degradation priors. These priors dynamically condition the MOS2D modules, facilitating adaptive and context-aware restoration. Extensive experiments and ablation studies demonstrate that MODEM achieves state-of-the-art results across multiple benchmarks and weather types, highlighting its effectiveness in modeling complex degradation dynamics. Our code will be released at https://github.com/hainuo-wang/MODEM.git.

Problem

• Estimating non-uniform weather-induced image degradation
• Restoring images with adaptive context-aware strategies
• Disentangling global and local degradation priors

Innovation

• Morton-Order 2D-Selective-Scan Module captures dependencies
• Dual Degradation Estimation Module disentangles global and local priors
• Dynamic conditioning enables adaptive context-aware restoration