The Second LoViF 2026 Challenge on Real-World All-in-One Image Restoration: Methods and Results

2026-07-23

AI Summary

This work addresses the challenge of real-world image degradation, where multiple distortions—such as blur, low light, haze, rain, and snow—often coexist. To tackle this problem, the authors propose and organize the first algorithmic competition dedicated to unified image restoration. A comprehensive benchmark encompassing diverse real-world degradations is established to systematically evaluate model performance in terms of accuracy, robustness, and cross-domain generalization. The competition adopts a deep learning–based unified restoration framework that integrates multi-degradation modeling and robust training strategies, attracting participation from 158 teams. The resulting advances significantly enhance real-world image restoration performance and establish a new benchmark for low-level vision research.

Abstract

This paper presents a review of the second LoViF Challenge on Real-World All-in-One Image Restoration. The challenge aims to advance unified image restoration under diverse real-world degradation conditions, including blur, low-light, haze, rain, and snow. It provides a common benchmark for evaluating the restoration accuracy, robustness, and generalization capability of models across multiple degradation categories within a unified framework. The competition attracted 158 registered participants, and 20 teams were included in the final ranking after their submitted results were successfully reproduced and verified. This report provides a comprehensive analysis of the submitted solutions and corresponding results, highlighting recent advances in real-world all-in-one image restoration. The summarized methods and empirical findings reveal effective design strategies and establish an updated benchmark for future research in real-world low-level vision.

Problem

• image restoration
• real-world degradation
• all-in-one
• low-level vision
• unified framework

Innovation

• all-in-one image restoration
• real-world degradation
• unified framework
• image restoration benchmark
• low-level vision