mlsanityData to 14 Oct 2026

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

arXiv 2508.13479 ↗First posted 19 Aug 2025cs.CV eess.IVcited by 8

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Builds on 39 of its 76 references that are in the map. First posted on arXiv 19 Aug 2025.

Builds on

39 of 76 references.

References · 39

  1. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  4. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  5. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  6. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 9,122
  7. 2017Enhanced Deep Residual Networks for Single Image Super-Resolutioncited by 1,552
  8. 20163D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotationcited by 1,476
  9. 2023Improving and generalizing flow-based generative models with minibatch optimal transportcited by 879
  10. 2022Simple Baselines for Image Restorationcited by 708
  11. 2018Image Inpainting for Irregular Holes Using Partial Convolutionscited by 505
  12. 2023Symbolic Discovery of Optimization Algorithmscited by 434
27 more
  1. 2021GAN Inversion: A Surveycited by 367
  2. 2023Image Restoration with Mean-Reverting Stochastic Differential Equationscited by 183
  3. 2017HDR image reconstruction from a single exposure using deep CNNscited by 167
  4. 2020Single-Image HDR Reconstruction by Learning to Reverse the Camera Pipelinecited by 132
  5. 2018ExpandNet: A Deep Convolutional Neural Network for High Dynamic Range Expansion from Low Dynamic Range Contentcited by 89
  6. 2023Refusion: Enabling Large-Size Realistic Image Restoration with Latent-Space Diffusion Modelscited by 86
  7. 2018How good is my GAN?cited by 74
  8. 2020Single Image HDR Reconstruction Using a CNN with Masked Features and Perceptual Losscited by 71
  9. 2025SceneSplat: Gaussian Splatting-based Scene Understanding with Vision-Language Pretrainingcited by 52
  10. 2019Deep SR-ITM: Joint Learning of Super-Resolution and Inverse Tone-Mapping for 4K UHD HDR Applicationscited by 39
  11. 2022Masked Jigsaw Puzzle: A Versatile Position Embedding for Vision Transformerscited by 33
  12. 2023Alignment-free HDR Deghosting with Semantics Consistent Transformercited by 32
  13. 2019JSI-GAN: GAN-Based Joint Super-Resolution and Inverse Tone-Mapping with Pixel-Wise Task-Specific Filters for UHD HDR Videocited by 31
  14. 2025The Tenth NTIRE 2025 Efficient Super-Resolution Challenge Reportcited by 26
  15. 2018Deep Chain HDRI: Reconstructing a High Dynamic Range Image from a Single Low Dynamic Range Imagecited by 25
  16. 2024LEDiff: Latent Exposure Diffusion for HDR Generationcited by 22
  17. 2021Cascaded Cross MLP-Mixer GANs for Cross-View Image Translationcited by 21
  18. 2022GlowGAN: Unsupervised Learning of HDR Images from LDR Images in the Wildcited by 21
  19. 2022Single-Image HDR Reconstruction by Multi-Exposure Generationcited by 20
  20. 2021Luminance Attentive Networks for HDR Image and Panorama Reconstructioncited by 18
  21. 2024Bracket Diffusion: HDR Image Generation by Consistent LDR Denoisingcited by 15
  22. 2024Sharing Key Semantics in Transformer Makes Efficient Image Restorationcited by 14
  23. 2022SDRTV-to-HDRTV via Hierarchical Dynamic Context Feature Mappingcited by 13
  24. 2024Intrinsic Single-Image HDR Reconstructioncited by 11
  25. 2024Semantic Aware Diffusion Inverse Tone Mappingcited by 7
  26. 2025Elucidating and Endowing the Diffusion Training Paradigm for General Image Restorationcited by 3
  27. 2024Hierarchical Cross-Attention Network for Virtual Try-Oncited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 5; 2026: 3.

8 papers.

  1. 2026The Eleventh NTIRE 2026 Efficient Super-Resolution Challenge Reportcited by 25
  2. 2025AIM 2025 Low-light RAW Video Denoising Challenge: Dataset, Methods and Resultscited by 14
  3. 2025AIM 2025 Challenge on High FPS Motion Deblurring: Methods and Resultscited by 2
  4. 2025AIM 2025 Challenge on Real-World RAW Image Denoisingcited by 2
  5. 2025Efficient Real-World Deblurring using Single Images: AIM 2025 Challenge Reportcited by 2
  6. 2026ExpoCM: Exposure-Aware One-Step Generative Single-Image HDR Reconstructioncited by 1
  7. 2025Efficient Perceptual Image Super Resolution: AIM 2025 Study and Benchmarkcited by 0
  8. 2026ExpandDiff: Dynamic Range Expanding Diffusion for Single-Image HDR Reconstructioncited by 0