NTIRE 2025 Challenge on Low Light Image Enhancement: Methods and Results

2025-10-15

AI Summary

This paper addresses the challenges of insufficient brightness, blurred details, and severe noise corruption in low-light images under complex and dynamic scenes. To systematically evaluate state-of-the-art low-light image enhancement methods, an international competition involving 762 researchers worldwide was organized. A unified deep learning framework is proposed, integrating illumination estimation, image restoration, and adaptive noise suppression modules—enabling simultaneous preservation of color fidelity and significant improvements in detail clarity and perceptual quality. Solutions from the top 28 teams empirically validate the effectiveness of this technical approach. The study advances the establishment of a more robust and generalizable benchmark and evaluation protocol for low-light enhancement, thereby providing scalable, application-oriented solutions for real-world scenarios such as nighttime surveillance and autonomous driving.

Technology Category

• Computer Vision: Low Level & Physics-based Vision
• Search and Optimization: Learning to Search
• Intelligent Robots: State Estimation

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Security and Privacy: Privacy-enhancing technologies
• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods

Abstract

This paper presents a comprehensive review of the NTIRE 2025 Low-Light Image Enhancement (LLIE) Challenge, highlighting the proposed solutions and final outcomes. The objective of the challenge is to identify effective networks capable of producing brighter, clearer, and visually compelling images under diverse and challenging conditions. A remarkable total of 762 participants registered for the competition, with 28 teams ultimately submitting valid entries. This paper thoroughly evaluates the state-of-the-art advancements in LLIE, showcasing the significant progress.

Problem

• Enhancing low-light images for better visibility
• Developing networks for brighter and clearer images
• Evaluating solutions under challenging lighting conditions

Innovation

• Deep learning networks enhance low-light images
• Solutions produce brighter and clearer images
• Challenge evaluates state-of-the-art enhancement methods