AIM 2025 challenge on Inverse Tone Mapping Report: Methods and Results

2025-08-18

AI Summary

This paper addresses the challenge of inverse tone mapping (ITM)—reconstructing high-dynamic-range (HDR) images from single low-dynamic-range (LDR) inputs—by proposing a unified framework that jointly optimizes perceptual fidelity and numerical consistency. Leveraging insights from an international ITM competition involving 67 teams and 319 valid submissions, we systematically analyze and distill multiple deep learning–driven enhancement strategies, including perceptual loss modeling, luminance-chrominance decoupled reconstruction, and specialized evaluation metrics such as PU21-PSNR. Our method achieves state-of-the-art HDR reconstruction quality, attaining a peak PU21-PSNR of 29.22 dB—the highest reported to date. This result establishes a new performance benchmark and technical paradigm for ITM research, advancing both quantitative accuracy and perceptual realism in single-image HDR recovery.

Technology Category

• Computer Vision: Image and Video Retrieval
• Search and Optimization: Learning to Search
• Machine Learning: Imitation Learning & Inverse Reinforcement Learning

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Responsible Web: Data and user privacy-enhancing technologies for the Web

Abstract

This paper presents a comprehensive review of the AIM 2025 Challenge on Inverse Tone Mapping (ITM). The challenge aimed to push forward the development of effective ITM algorithms for HDR image reconstruction from single LDR inputs, focusing on perceptual fidelity and numerical consistency. A total of extbf{67} participants submitted extbf{319} valid results, from which the best five teams were selected for detailed analysis. This report consolidates their methodologies and performance, with the lowest PU21-PSNR among the top entries reaching 29.22 dB. The analysis highlights innovative strategies for enhancing HDR reconstruction quality and establishes strong benchmarks to guide future research in inverse tone mapping.

Problem

• Develops ITM algorithms for HDR reconstruction
• Enhances perceptual fidelity and numerical consistency
• Establishes benchmarks for inverse tone mapping

Innovation

• Inverse Tone Mapping algorithms for HDR reconstruction
• Single LDR input conversion with perceptual fidelity
• PU21-PSNR benchmarked enhancement strategies