mlsanityData to 14 Oct 2026

BSRAW: Improving Blind RAW Image Super-Resolution

arXiv 2312.15487 ↗First posted 24 Dec 2023eess.IV cs.CVcited by 11

Not on the map. Why?

Abstract (arXiv)

In smartphones and compact cameras, the Image Signal Processor (ISP) transforms the RAW sensor image into a human-readable sRGB image. Most popular super-resolution methods depart from a sRGB image and upscale it further, improving its quality. However, modeling the degradations in the sRGB domain is complicated because of the non-linear ISP transformations. Despite this known issue, only a few methods work directly with RAW images and tackle real-world sensor degradations. We tackle blind image super-resolution in the RAW domain. We design a realistic degradation pipeline tailored specifically for training models with raw sensor data. Our approach considers sensor noise, defocus, exposure, and other common issues. Our BSRAW models trained with our pipeline can upscale real-scene RAW images and improve their quality. As part of this effort, we also present a new DSLM dataset and benchmark for this task.

Key facts. Cited by 11 papers in the map (data through 14 Oct 2026). Builds on 51 of its 81 references that are in the map. First posted on arXiv 24 Dec 2023.

Builds on

51 of 81 references.

References · 51

  1. 2017Attention Is All You Needcited by 60,361
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2021SwinIR: Image Restoration Using Swin Transformercited by 1,887
  4. 2021Restormer: Efficient Transformer for High-Resolution Image Restorationcited by 1,627
  5. 2016Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoisingcited by 1,358
  6. 2018ESRGAN: Enhanced Super-Resolution Generative Adversarial Networkscited by 1,254
  7. 2021Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Datacited by 970
  8. 2021Uformer: A General U-Shaped Transformer for Image Restorationcited by 866
  9. 2018Residual Dense Network for Image Super-Resolutioncited by 799
  10. 2022Simple Baselines for Image Restorationcited by 708
  11. 2021Designing a Practical Degradation Model for Deep Blind Image Super-Resolutioncited by 529
  12. 2020Plug-and-Play Image Restoration with Deep Denoiser Priorcited by 470
38 more
  1. 2018Learning to See in the Darkcited by 460
  2. 2019Toward Real-World Single Image Super-Resolution: A New Benchmark and A New Modelcited by 403
  3. 2020Deep Unfolding Network for Image Super-Resolutioncited by 254
  4. 2018Unprocessing Images for Learned Raw Denoisingcited by 250
  5. 2020CycleISP: Real Image Restoration via Improved Data Synthesiscited by 213
  6. 2017Benchmarking Denoising Algorithms with Real Photographscited by 209
  7. 2017Burst Denoising with Kernel Prediction Networkscited by 157
  8. 2019Zoom To Learn, Learn To Zoomcited by 115
  9. 2019Neural Blind Deconvolution Using Deep Priorscited by 113
  10. 2020Replacing Mobile Camera ISP with a Single Deep Learning Modelcited by 108
  11. 2018To learn image super-resolution, use a GAN to learn how to do image degradation firstcited by 94
  12. 2021Invertible Image Signal Processingcited by 94
  13. 2018DeepISP: Towards Learning an End-to-End Image Processing Pipelinecited by 88
  14. 2022Practical Blind Image Denoising via Swin-Conv-UNet and Data Synthesiscited by 86
  15. 2021Deep Burst Super-Resolutioncited by 83
  16. 2020Supervised Raw Video Denoising with a Benchmark Dataset on Dynamic Scenescited by 77
  17. 2020Practical Deep Raw Image Denoising on Mobile Devicescited by 76
  18. 2022Swin2SR: SwinV2 Transformer for Compressed Image Super-Resolution and Restorationcited by 73
  19. 2019Unsupervised Learning for Real-World Super-Resolutioncited by 64
  20. 2021Mobile Computational Photography: A Tourcited by 62
  21. 2021Rethinking Noise Synthesis and Modeling in Raw Denoisingcited by 62
  22. 2019Towards Real Scene Super-Resolution with Raw Imagescited by 44
  23. 2022Model-Based Image Signal Processors via Learnable Dictionariescited by 43
  24. 2019CameraNet: A Two-Stage Framework for Effective Camera ISP Learningcited by 38
  25. 2021Learned Smartphone ISP on Mobile NPUs with Deep Learning, Mobile AI 2021 Challenge: Reportcited by 34
  26. 2019Learning Raw Image Denoising with Bayer Pattern Unification and Bayer Preserving Augmentationcited by 30
  27. 2021Towards Low Light Enhancement with RAW Imagescited by 26
  28. 2022Day-to-Night Image Synthesis for Training Nighttime Neural ISPscited by 23
  29. 2020Raw Image Deblurringcited by 22
  30. 2021Improving Single-Image Defocus Deblurring: How Dual-Pixel Images Help Through Multi-Task Learningcited by 20
  31. 2022Real-RawVSR: Real-World Raw Video Super-Resolution with a Benchmark Datasetcited by 19
  32. 2020A Multi-Hypothesis Approach to Color Constancycited by 18
  33. 2020Low-light Image Restoration with Short- and Long-exposure Raw Pairscited by 18
  34. 2022Perceptual Image Enhancement for Smartphone Real-Time Applicationscited by 18
  35. 2022Rawgment: Noise-Accounted RAW Augmentation Enables Recognition in a Wide Variety of Environmentscited by 18
  36. 2022Noise2NoiseFlow: Realistic Camera Noise Modeling without Clean Imagescited by 17
  37. 2021Exploiting Raw Images for Real-Scene Super-Resolutioncited by 12
  38. 2018Convolutional Deblurring for Natural Imagingcited by 9

50 most cited of 51 All 51 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 4; 2025: 3; 2026: 4.

11 papers.

  1. 2024Unveiling Hidden Details: A RAW Data-Enhanced Paradigm for Real-World Super-Resolutioncited by 26
  2. 2025NTIRE 2025 Challenge on RAW Image Restoration and Super-Resolutioncited by 9
  3. 2024Toward Efficient Deep Blind RAW Image Restorationcited by 7
  4. 2024Deep RAW Image Super-Resolution. A NTIRE 2024 Challenge Surveycited by 6
  5. 2025RAW Image Reconstruction from RGB on Smartphones. NTIRE 2025 Challenge Reportcited by 4
  6. 2024Simple Image Signal Processing using Global Context Guidancecited by 2
  7. 2025ICME 2025 Grand Challenge on Video Super-Resolution for Video Conferencingcited by 1
  8. 2026RAW-Domain Degradation Models for Realistic Smartphone Super-Resolutioncited by 0
  9. 2026MERIT: Multi-domain Efficient RAW Image Translationcited by 0
  10. 2026ENAF: A Multi-Exit Network with an Adaptive Patch Fusion for Large Image Super Resolutioncited by 0
  11. 2026Benchmarking RAW and RGB Restoration in Image Signal Processorscited by 0