LoViF 2026 The First Challenge on Weather Removal in Videos

2026-04-12

AI Summary

This work addresses the problem of video degradation caused by adverse weather conditions such as rain and snow, proposing the first Video Deraining and Desnowing Challenge to restore visually plausible and temporally consistent clear videos. The initiative introduces the short-form Weather-Robust Video (WRV) dataset, comprising both synthetic and real paired frames, and establishes a multidimensional evaluation protocol that jointly assesses fidelity and perceptual quality while emphasizing structural preservation and temporal coherence. The challenge attracted 37 participating teams, yielding five valid submissions, and has significantly advanced the development of novel video-level deraining and desnowing algorithms, thereby fostering substantial progress in this emerging research area.

Technology Category

• Computer Vision: Video Understanding & Activity Analysis
• Machine Learning: Adversarial Learning & Robustness
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning

Application Category

• Responsible Web: Human-perceived consequences of algorithmic deployment on the web
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Systems and Infrastructure for Web, Mobile and WoT: Experiences and lessons learnt from Web-based algorithms and system deployments

Abstract

This paper presents a review of the LoViF 2026 Challenge on Weather Removal in Videos. The challenge encourages the development of methods for restoring clean videos from inputs degraded by adverse weather conditions such as rain and snow, with an emphasis on achieving visually plausible and temporally consistent results while preserving scene structure and motion dynamics. To support this task, we introduce a new short-form WRV dataset tailored for video weather removal. It consists of 18 videos 1,216 synthesized frames paired with 1,216 real-world ground-truth frames at a resolution of 832 x 480, and is split into training, validation, and test sets with a ratio of 1:1:1. The goal of this challenge is to advance robust and realistic video restoration under real-world weather conditions, with evaluation protocols that jointly consider fidelity and perceptual quality. The challenge attracted 37 participants and received 5 valid final submissions with corresponding fact sheets, contributing to progress in weather removal for videos. The project is publicly available at https://www.codabench.org/competitions/13462/.

Problem

• weather removal
• video restoration
• adverse weather
• temporal consistency
• scene structure

Innovation

• video weather removal
• temporal consistency
• WRV dataset
• perceptual quality
• adverse weather restoration