mlsanityData to 14 Oct 2026

Reversed Image Signal Processing and RAW Reconstruction. AIM 2022 Challenge Report

arXiv 2210.11153 ↗First posted 20 Oct 2022eess.IV cs.CVcited by 11

Not on the map. Why?

Abstract (arXiv)

Cameras capture sensor RAW images and transform them into pleasant RGB images, suitable for the human eyes, using their integrated Image Signal Processor (ISP). Numerous low-level vision tasks operate in the RAW domain (e.g. image denoising, white balance) due to its linear relationship with the scene irradiance, wide-range of information at 12bits, and sensor designs. Despite this, RAW image datasets are scarce and more expensive to collect than the already large and public RGB datasets. This paper introduces the AIM 2022 Challenge on Reversed Image Signal Processing and RAW Reconstruction. We aim to recover raw sensor images from the corresponding RGBs without metadata and, by doing this, "reverse" the ISP transformation. The proposed methods and benchmark establish the state-of-the-art for this low-level vision inverse problem, and generating realistic raw sensor readings can potentially benefit other tasks such as denoising and super-resolution.

Key facts. Cited by 11 papers in the map (data through 14 Oct 2026). Builds on 33 of its 54 references that are in the map. First posted on arXiv 20 Oct 2022.

Builds on

33 of 54 references.

References · 33

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  3. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  4. 2018CBAM: Convolutional Block Attention Modulecited by 2,477
  5. 2016Identity Mappings in Deep Residual Networkscited by 1,965
  6. 2018ESRGAN: Enhanced Super-Resolution Generative Adversarial Networkscited by 1,254
  7. 2017PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volumecited by 968
  8. 2018Residual Dense Network for Image Super-Resolutioncited by 799
  9. 2022Simple Baselines for Image Restorationcited by 708
  10. 2017The Perception-Distortion Tradeoffcited by 587
  11. 2018Unprocessing Images for Learned Raw Denoisingcited by 250
  12. 2021HINet: Half Instance Normalization Network for Image Restorationcited by 237
21 more
  1. 2020CycleISP: Real Image Restoration via Improved Data Synthesiscited by 213
  2. 2020Learning Image-adaptive 3D Lookup Tables for High Performance Photo Enhancement in Real-timecited by 163
  3. 2020Replacing Mobile Camera ISP with a Single Deep Learning Modelcited by 108
  4. 2021Invertible Image Signal Processingcited by 94
  5. 2018DeepISP: Towards Learning an End-to-End Image Processing Pipelinecited by 88
  6. 2021Mobile Computational Photography: A Tourcited by 62
  7. 2021Improving Image Restoration by Revisiting Global Information Aggregationcited by 61
  8. 2020AIM 2020 Challenge on Learned Image Signal Processing Pipelinecited by 44
  9. 2021Learning RAW-to-sRGB Mappings with Inaccurately Aligned Supervisioncited by 43
  10. 2022Model-Based Image Signal Processors via Learnable Dictionariescited by 43
  11. 2020NTIRE 2020 Challenge on Spectral Reconstruction from an RGB Imagecited by 30
  12. 2021A New Journey from SDRTV to HDRTVcited by 30
  13. 2020CIE XYZ Net: Unprocessing Images for Low-Level Computer Vision Taskscited by 29
  14. 2021NTIRE 2021 Challenge on Burst Super-Resolution: Methods and Resultscited by 22
  15. 2022Learning sRGB-to-Raw-RGB De-rendering with Content-Aware Metadatacited by 22
  16. 2022AIM 2022 Challenge on Super-Resolution of Compressed Image and Video: Dataset, Methods and Resultscited by 20
  17. 2021Semi-Supervised Raw-to-Raw Mappingcited by 16
  18. 2021Instagram Filter Removal on Fashionable Imagescited by 8
  19. 2022AIM 2022 Challenge on Instagram Filter Removal: Methods and Resultscited by 6
  20. 2022Patch-wise Contrastive Style Learning for Instagram Filter Removalcited by 5
  21. 2022Reversing Image Signal Processors by Reverse Style Transferringcited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 5; 2023: 2; 2024: 1; 2025: 2; 2026: 1.

11 papers.

  1. 2022Efficient and Accurate Quantized Image Super-Resolution on Mobile NPUs, Mobile AI & AIM 2022 challenge: Reportcited by 16
  2. 2022Learned Smartphone ISP on Mobile GPUs with Deep Learning, Mobile AI & AIM 2022 Challenge: Reportcited by 13
  3. 2024RAW-Diffusion: RGB-Guided Diffusion Models for High-Fidelity RAW Image Generationcited by 8
  4. 2023Self-Supervised Reversed Image Signal Processing via Reference-Guided Dynamic Parameter Selectioncited by 5
  5. 2022Efficient Single-Image Depth Estimation on Mobile Devices, Mobile AI & AIM 2022 Challenge: Reportcited by 4
  6. 2025RAW Image Reconstruction from RGB on Smartphones. NTIRE 2025 Challenge Reportcited by 4
  7. 2022Power Efficient Video Super-Resolution on Mobile NPUs with Deep Learning, Mobile AI & AIM 2022 challenge: Reportcited by 3
  8. 2023Spectral Sensitivity Estimation Without a Cameracited by 3
  9. 2022Realistic Bokeh Effect Rendering on Mobile GPUs, Mobile AI & AIM 2022 challenge: Reportcited by 2
  10. 2025Edit-aware RAW Reconstructioncited by 0
  11. 2026Linear Image Generation by Synthesizing Exposure Bracketscited by 0