Traffic Image Restoration under Adverse Weather via Frequency-Aware Mamba

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Pan, Liwen, Wang, Longguang, Gao, Guangwei, Wang, Jun, Shi, Jun, Li, Juncheng
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866918230025568256
author Pan, Liwen
Wang, Longguang
Gao, Guangwei
Wang, Jun
Shi, Jun
Li, Juncheng
author_facet Pan, Liwen
Wang, Longguang
Gao, Guangwei
Wang, Jun
Shi, Jun
Li, Juncheng
contents Traffic image restoration under adverse weather conditions remains a critical challenge for intelligent transportation systems. Existing methods primarily focus on spatial-domain modeling but neglect frequency-domain priors. Although the emerging Mamba architecture excels at long-range dependency modeling through patch-wise correlation analysis, its potential for frequency-domain feature extraction remains unexplored. To address this, we propose Frequency-Aware Mamba (FAMamba), a novel framework that integrates frequency guidance with sequence modeling for efficient image restoration. Our architecture consists of two key components: (1) a Dual-Branch Feature Extraction Block (DFEB) that enhances local-global interaction via bidirectional 2D frequency-adaptive scanning, dynamically adjusting traversal paths based on sub-band texture distributions; and (2) a Prior-Guided Block (PGB) that refines texture details through wavelet-based high-frequency residual learning, enabling high-quality image reconstruction with precise details. Meanwhile, we design a novel Adaptive Frequency Scanning Mechanism (AFSM) for the Mamba architecture, which enables the Mamba to achieve frequency-domain scanning across distinct subgraphs, thereby fully leveraging the texture distribution characteristics inherent in subgraph structures. Extensive experiments demonstrate the efficiency and effectiveness of FAMamba.
format Preprint
id arxiv_https___arxiv_org_abs_2512_03852
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Traffic Image Restoration under Adverse Weather via Frequency-Aware Mamba
Pan, Liwen
Wang, Longguang
Gao, Guangwei
Wang, Jun
Shi, Jun
Li, Juncheng
Computer Vision and Pattern Recognition
Traffic image restoration under adverse weather conditions remains a critical challenge for intelligent transportation systems. Existing methods primarily focus on spatial-domain modeling but neglect frequency-domain priors. Although the emerging Mamba architecture excels at long-range dependency modeling through patch-wise correlation analysis, its potential for frequency-domain feature extraction remains unexplored. To address this, we propose Frequency-Aware Mamba (FAMamba), a novel framework that integrates frequency guidance with sequence modeling for efficient image restoration. Our architecture consists of two key components: (1) a Dual-Branch Feature Extraction Block (DFEB) that enhances local-global interaction via bidirectional 2D frequency-adaptive scanning, dynamically adjusting traversal paths based on sub-band texture distributions; and (2) a Prior-Guided Block (PGB) that refines texture details through wavelet-based high-frequency residual learning, enabling high-quality image reconstruction with precise details. Meanwhile, we design a novel Adaptive Frequency Scanning Mechanism (AFSM) for the Mamba architecture, which enables the Mamba to achieve frequency-domain scanning across distinct subgraphs, thereby fully leveraging the texture distribution characteristics inherent in subgraph structures. Extensive experiments demonstrate the efficiency and effectiveness of FAMamba.
title Traffic Image Restoration under Adverse Weather via Frequency-Aware Mamba
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2512.03852