mlsanityData to 7 Oct 2026

Invertible Image Signal Processing

arXiv 2103.15061 ↗First posted 28 Mar 2021eess.IV cs.CVcited by 94

Not on the map. Why?

Abstract (arXiv)

Unprocessed RAW data is a highly valuable image format for image editing and computer vision. However, since the file size of RAW data is huge, most users can only get access to processed and compressed sRGB images. To bridge this gap, we design an Invertible Image Signal Processing (InvISP) pipeline, which not only enables rendering visually appealing sRGB images but also allows recovering nearly perfect RAW data. Due to our framework's inherent reversibility, we can reconstruct realistic RAW data instead of synthesizing RAW data from sRGB images without any memory overhead. We also integrate a differentiable JPEG compression simulator that empowers our framework to reconstruct RAW data from JPEG images. Extensive quantitative and qualitative experiments on two DSLR demonstrate that our method obtains much higher quality in both rendered sRGB images and reconstructed RAW data than alternative methods.

Key facts. Cited by 94 papers in the map (data through 7 Oct 2026). Builds on 24 of its 48 references that are in the map. First posted on arXiv 28 Mar 2021.

Builds on

24 of 48 references.

References · 24

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  2. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
  3. 2016Density estimation using Real NVPcited by 2,029
  4. 2018Glow: Generative Flow with Invertible 1x1 Convolutionscited by 1,539
  5. 2014NICE: Non-linear Independent Components Estimationcited by 1,052
  6. 2018Learning to See in the Darkcited by 459
  7. 2019Flow++: Improving Flow-Based Generative Models with Variational Dequantization and Architecture Designcited by 258
  8. 2018Unprocessing Images for Learned Raw Denoisingcited by 250
  9. 2019Differentiable Soft Quantization: Bridging Full-Precision and Low-Bit Neural Networkscited by 234
  10. 2020CycleISP: Real Image Restoration via Improved Data Synthesiscited by 212
  11. 2017Benchmarking Denoising Algorithms with Real Photographscited by 209
  12. 2017HDR image reconstruction from a single exposure using deep CNNscited by 167
12 more
  1. 2017Burst Denoising with Kernel Prediction Networkscited by 156
  2. 2020Single-Image HDR Reconstruction by Learning to Reverse the Camera Pipelinecited by 131
  3. 2019Zoom To Learn, Learn To Zoomcited by 114
  4. 2020Invertible Image Rescalingcited by 92
  5. 2018DeepISP: Towards Learning an End-to-End Image Processing Pipelinecited by 88
  6. 2020Polarized Reflection Removal with Perfect Alignment in the Wildcited by 69
  7. 2019Towards Real Scene Super-Resolution with Raw Imagescited by 44
  8. 2019CameraNet: A Two-Stage Framework for Effective Camera ISP Learningcited by 38
  9. 2015Convolutional Color Constancycited by 36
  10. 2021Robust Reflection Removal with Reflection-free Flash-only Cuescited by 34
  11. 2020CIE XYZ Net: Unprocessing Images for Low-Level Computer Vision Taskscited by 29
  12. 2017Exposure: A White-Box Photo Post-Processing Frameworkcited by 27

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 5; 2022: 17; 2023: 21; 2024: 11; 2025: 21; 2026: 19.

94 papers.

Sort:

By area:

  1. 2021Enhanced Invertible Encoding for Learned Image Compressioncited by 102
  2. 2022You Only Need 90K Parameters to Adapt Light: A Light Weight Transformer for Image Enhancement and Exposure Correctioncited by 81
  3. 2022Towards Blind Watermarking: Combining Invertible and Non-invertible Mechanismscited by 61
  4. 2022Model-Based Image Signal Processors via Learnable Dictionariescited by 43
  5. 2023RawHDR: High Dynamic Range Image Reconstruction from a Single Raw Imagecited by 31
  6. 2023ParamISP: Learned Forward and Inverse ISPs using Camera Parameterscited by 23
  7. 2022Learning to Immunize Images for Tamper Localization and Self-Recoverycited by 19
  8. 2024RAW-Adapter: Adapting Pre-trained Visual Model to Camera RAW Imagescited by 19
  9. 2023Raw Image Reconstruction with Learned Compact Metadatacited by 18
  10. 2022Invertible Rescaling Network and Its Extensionscited by 15
  11. 2022D2HNet: Joint Denoising and Deblurring with Hierarchical Network for Robust Night Image Restorationcited by 14
  12. 2022Robust Reflection Removal with Flash-only Cues in the Wildcited by 14
38 more
  1. 2021IICNet: A Generic Framework for Reversible Image Conversioncited by 13
  2. 2023Differentiable JPEG: The Devil is in the Detailscited by 13
  3. 2021A Categorized Reflection Removal Dataset with Diverse Real-world Scenescited by 12
  4. 2021From Image to Imuge: Immunized Image Generationcited by 11
  5. 2022Scale-arbitrary Invertible Image Downscalingcited by 11
  6. 2022Bitwidth Heterogeneous Federated Learning with Progressive Weight Dequantizationcited by 11
  7. 2022Reversed Image Signal Processing and RAW Reconstruction. AIM 2022 Challenge Reportcited by 11
  8. 2023BSRAW: Improving Blind RAW Image Super-Resolutioncited by 11
  9. 2024Rawformer: Unpaired Raw-to-Raw Translation for Learnable Camera ISPscited by 11
  10. 2023DRAW: Defending Camera-shooted RAW against Image Manipulationcited by 10
  11. 2025Time-Aware Auto White Balance in Mobile Photographycited by 10
  12. 2022Transform your Smartphone into a DSLR Camera: Learning the ISP in the Wildcited by 9
  13. 2023Self-Asymmetric Invertible Network for Compression-Aware Image Rescalingcited by 9
  14. 2023Information-containing Adversarial Perturbation for Combating Facial Manipulation Systemscited by 9
  15. 2023Beyond Learned Metadata-based Raw Image Reconstructioncited by 9
  16. 2025NTIRE 2025 Challenge on RAW Image Restoration and Super-Resolutioncited by 9
  17. 2024RAW-Diffusion: RGB-Guided Diffusion Models for High-Fidelity RAW Image Generationcited by 8
  18. 2025ISPDiffuser: Learning RAW-to-sRGB Mappings with Texture-Aware Diffusion Models and Histogram-Guided Color Consistencycited by 7
  19. 2023Real-time 6K Image Rescaling with Rate-distortion Optimizationcited by 6
  20. 2023Learning Many-to-Many Mapping for Unpaired Real-World Image Super-resolution and Downscalingcited by 6
  21. 2023THInImg: Cross-modal Steganography for Presenting Talking Heads in Imagescited by 6
  22. 2024ResVR: Joint Rescaling and Viewport Rendering of Omnidirectional Imagescited by 6
  23. 2023Self-Supervised Reversed Image Signal Processing via Reference-Guided Dynamic Parameter Selectioncited by 5
  24. 2023Realistic Noise Synthesis with Diffusion Modelscited by 5
  25. 2024MetaISP -- Exploiting Global Scene Structure for Accurate Multi-Device Color Renditioncited by 5
  26. 2025Dark-ISP: Enhancing RAW Image Processing for Low-Light Object Detectioncited by 5
  27. 2023Generating Robust Adversarial Examples against Online Social Networks (OSNs)cited by 4
  28. 2025Color Matching Using Hypernetwork-Based Kolmogorov-Arnold Networkscited by 4
  29. 2025RAW Image Reconstruction from RGB on Smartphones. NTIRE 2025 Challenge Reportcited by 4
  30. 2026RAW-Flow: Advancing RGB-to-RAW Image Reconstruction with Deterministic Latent Flow Matchingcited by 4
  31. 2022Reversing Image Signal Processors by Reverse Style Transferringcited by 3
  32. 2023Efficient HDR Reconstruction from Real-World Raw Imagescited by 3
  33. 2023LDM-ISP: Enhancing Neural ISP for Low Light with Latent Diffusion Modelscited by 3
  34. 2024A Learnable Color Correction Matrix for RAW Reconstructioncited by 3
  35. 2024RAWMamba: Unified sRGB-to-RAW De-rendering With State Space Modelcited by 3
  36. 2026RAWild: Sensor-Agnostic RAW Object Detection via Physics-Guided Curve and Grid Modelingcited by 3
  37. 2024Simple Image Signal Processing using Global Context Guidancecited by 2
  38. 2025SimROD: A Simple Baseline for Raw Object Detection with Global and Local Enhancementscited by 2

50 most cited of 94 All 94 (JSON)