Clear Roads, Clear Vision: Advancements in Multi-Weather Restoration for Smart Transportation

2025-10-10

AI Summary

Adverse weather conditions (e.g., haze, rain, snow) induce severe image degradation, critically undermining the reliability of vision-based tasks—such as autonomous driving and traffic surveillance—in intelligent transportation systems (ITS). This paper presents a systematic survey of multi-weather image/video restoration techniques tailored for ITS. We propose the first unified taxonomy, organizing methods along two orthogonal dimensions: model paradigms (traditional priors, CNNs, Transformers, diffusion models, and vision-language models) and task architectures (single-task → multi-task → end-to-end unified). We further integrate day-night adaptation strategies and standardized evaluation protocols, comprehensively cataloging mainstream datasets and benchmarks. Key challenges—including compound degradation modeling, real-time lightweight deployment, and AI-agent collaborative restoration—are identified and analyzed. To support community advancement, we open-source a continuously updated, curated literature repository, establishing a structured knowledge infrastructure and a roadmap for future research.

Technology Category

• Computer Vision: Multi-modal Vision
• Intelligent Robots: Multi-Robot Systems
• Machine Learning: Transfer, Domain Adaptation, Multi-Task Learning

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Adverse weather conditions such as haze, rain, and snow significantly degrade the quality of images and videos, posing serious challenges to intelligent transportation systems (ITS) that rely on visual input. These degradations affect critical applications including autonomous driving, traffic monitoring, and surveillance. This survey presents a comprehensive review of image and video restoration techniques developed to mitigate weather-induced visual impairments. We categorize existing approaches into traditional prior-based methods and modern data-driven models, including CNNs, transformers, diffusion models, and emerging vision-language models (VLMs). Restoration strategies are further classified based on their scope: single-task models, multi-task/multi-weather systems, and all-in-one frameworks capable of handling diverse degradations. In addition, we discuss day and night time restoration challenges, benchmark datasets, and evaluation protocols. The survey concludes with an in-depth discussion on limitations in current research and outlines future directions such as mixed/compound-degradation restoration, real-time deployment, and agentic AI frameworks. This work aims to serve as a valuable reference for advancing weather-resilient vision systems in smart transportation environments. Lastly, to stay current with rapid advancements in this field, we will maintain regular updates of the latest relevant papers and their open-source implementations at https://github.com/ChaudharyUPES/A-comprehensive-review-on-Multi-weather-restoration

Problem

• Addressing weather-induced image degradation in transportation systems
• Surveying restoration techniques for multi-weather visual impairments
• Developing resilient vision models for smart transportation applications

Innovation

• Surveying traditional and data-driven restoration models
• Classifying single-task and multi-weather restoration frameworks
• Proposing future directions for real-time agentic AI