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

TL;DR

This survey consolidates advances in image and video restoration under adverse weather to support smart transportation systems. It categorizes approaches into traditional priors and modern data-driven methods, including CNNs, transformers, diffusion models, and vision-language guidance, with all-in-one and multi-weather architectures highlighted. The authors review datasets, loss functions, and experimental benchmarks, and discuss limitations such as data scarcity, video restoration under weather, and real-time deployment. They articulate future directions toward mixed/degraded conditions, real-time edge processing, domain adaptation, and agentic AI frameworks to enable robust, weather-resilient perception in ITS contexts.

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

Figures (4)

• Figure 1: Real-world haze, rain, and snow degradations in daytime and nighttime images.
• Figure 2: Synthetic image generation pipeline: atmospheric light settings combine with (i) a transmission map for depth-dependent haze, (ii) rain-streak overlays for rain, and (iii) snow-particle maps for snow, producing realistic hazy, rainy, and snowy scenes.
• Figure 3: The development timeline of hazy, rainy, snowy and multi-weather degraded image/video restoration approaches.
• Figure 4: Visual result analysis of the existing methods: UMVR kulkarni2022unified (TMM-22), KD 9879902 (CVPR-22), TW valanarasu2022transweather (CVPR-22), Diffusion ozdenizci2023restoring (TPAMI-23), WGWS 10204275 (CVPR-23) and DTMIR patil2023multi (ICCV-23) on complex situations of real-world weather degraded image restoration.