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

2025/08/19 by Chao Wang, Wang, Chao, Francesco Banterle +51 · 5 citations
Earth and Planetary Sciences · #3D Surveying and Cultural Heritage #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #FOS: Electrical engineering #Image and Video Processing (eess.IV) #Seismic Waves and Analysis #electronic engineering #information engineering

paper · pdf · doi:10.48550/arxiv.2508.13479

openalex publication_date 2025/08/19 · openalex created_date 2025/10/09 · openalex updated_date 2026/07/28

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 67 participants submitted 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.

Citations

• Efficient Real-World Deblurring using Single Images: AIM 2025 Challenge Report
• AIM 2025 Low-light RAW Video Denoising Challenge: Dataset, Methods and Results
• Elucidating and Endowing the Diffusion Training Paradigm for General Image Restoration
• The Tenth NTIRE 2025 Efficient Super-Resolution Challenge Report
• SceneSplat: Gaussian Splatting-based Scene Understanding with Vision-Language Pretraining
• LEDiff: Latent Exposure Diffusion for HDR Generation
• Hierarchical Cross-Attention Network for Virtual Try-On
• Intrinsic Single-Image HDR Reconstruction
• Sharing Key Semantics in Transformer Makes Efficient Image Restoration
• Semantic Aware Diffusion Inverse Tone Mapping
• Bracket Diffusion: HDR Image Generation by Consistent LDR Denoising
• Alignment-free HDR Deghosting with Semantics Consistent Transformer
• Refusion: Enabling Large-Size Realistic Image Restoration with Latent-Space Diffusion Models
• Symbolic Discovery of Optimization Algorithms
• Improving and generalizing flow-based generative models with minibatch optimal transport
• Image Restoration with Mean-Reverting Stochastic Differential Equations
• GlowGAN: Unsupervised Learning of HDR Images from LDR Images in the Wild
• Single-Image HDR Reconstruction by Multi-Exposure Generation
• SDRTV-to-HDRTV via Hierarchical Dynamic Context Feature Mapping
• Masked Jigsaw Puzzle: A Versatile Position Embedding for Vision Transformers
• Simple Baselines for Image Restoration
• High-Resolution Image Synthesis with Latent Diffusion Models
• High-Resolution Image Synthesis with Latent Diffusion Models
• Cascaded Cross MLP-Mixer GANs for Cross-View Image Translation
• Luminance Attentive Networks for HDR Image and Panorama Reconstruction
• GAN Inversion: A Survey
• Score-Based Generative Modeling through Stochastic Differential Equations
• An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
• Single-Image HDR Reconstruction by Learning to Reverse the Camera Pipeline
• JSI-GAN: GAN-Based Joint Super-Resolution and Inverse Tone-Mapping with Pixel-Wise Task-Specific Filters for UHD HDR Video
• Deep SR-ITM: Joint Learning of Super-Resolution and Inverse Tone-Mapping for 4K UHD HDR Applications
• How good is my GAN?
• Image Inpainting for Irregular Holes Using Partial Convolutions
• ExpandNet: A Deep Convolutional Neural Network for High Dynamic Range Expansion from Low Dynamic Range Content
• Enhanced Deep Residual Networks for Single Image Super-Resolution
• 3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation
• U-Net: Convolutional Networks for Biomedical Image Segmentation
• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Swin Transformer: Hierarchical Vision Transformer using Shifted Windows
• Swin Transformer: Hierarchical Vision Transformer using Shifted Windows

Cited by

• Efficient Real-World Deblurring using Single Images: AIM 2025 Challenge Report
• Efficient Perceptual Image Super Resolution: AIM 2025 Study and Benchmark
• AIM 2025 Challenge on Real-World RAW Image Denoising
• AIM 2025 Low-light RAW Video Denoising Challenge: Dataset, Methods and Results
• AIM 2025 Challenge on High FPS Motion Deblurring: Methods and Results
• AIM 2025 Rip Current Segmentation (RipSeg) Challenge Report

Related

• Lightweight Improved Residual Network for Efficient Inverse Tone Mapping
• Deep Inverse Tone Mapping Using LDR Based Learning for Estimating HDR Images with Absolute Luminance
• Lightness Modulated Deep Inverse Tone Mapping
• Deep Neural Networks for HDR imaging
• Explorable Tone Mapping Operators