mlsanityData to 7 Oct 2026

RAW-Adapter: Adapting Pre-trained Visual Model to Camera RAW Images

arXiv 2408.14802 ↗First posted 27 Aug 2024cs.CVcited by 19

Not on the map. Why?

Abstract (arXiv)

sRGB images are now the predominant choice for pre-training visual models in computer vision research, owing to their ease of acquisition and efficient storage. Meanwhile, the advantage of RAW images lies in their rich physical information under variable real-world challenging lighting conditions. For computer vision tasks directly based on camera RAW data, most existing studies adopt methods of integrating image signal processor (ISP) with backend networks, yet often overlook the interaction capabilities between the ISP stages and subsequent networks. Drawing inspiration from ongoing adapter research in NLP and CV areas, we introduce RAW-Adapter, a novel approach aimed at adapting sRGB pre-trained models to camera RAW data. RAW-Adapter comprises input-level adapters that employ learnable ISP stages to adjust RAW inputs, as well as model-level adapters to build connections between ISP stages and subsequent high-level networks. Additionally, RAW-Adapter is a general framework that could be used in various computer vision frameworks. Abundant experiments under different lighting conditions have shown our algorithm's state-of-the-art (SOTA) performance, demonstrating its effectiveness and efficiency across a range of real-world and synthetic datasets.

Key facts. Cited by 19 papers in the map (data through 7 Oct 2026). Builds on 54 of its 79 references that are in the map. First posted on arXiv 27 Aug 2024.

Builds on

54 of 79 references.

References · 54

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  4. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  5. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  6. 2023Segment Anythingcited by 8,158
  7. 2020End-to-End Object Detection with Transformerscited by 7,384
  8. 2019Parameter-Efficient Transfer Learning for NLPcited by 4,195
  9. 2021SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformerscited by 2,923
  10. 2020Implicit Neural Representations with Periodic Activation Functionscited by 2,214
  11. 2022Visual Prompt Tuningcited by 1,674
  12. 2019MMDetection: Open MMLab Detection Toolbox and Benchmarkcited by 1,379
38 more
  1. 2021Per-Pixel Classification is Not All You Need for Semantic Segmentationcited by 1,148
  2. 2022Vision Transformer Adapter for Dense Predictionscited by 564
  3. 2017Learning multiple visual domains with residual adapterscited by 553
  4. 2020Sparse R-CNN: End-to-End Object Detection with Learnable Proposalscited by 494
  5. 2018Learning to See in the Darkcited by 459
  6. 2023Segment Anything in High Qualitycited by 373
  7. 2022Tip-Adapter: Training-free Adaption of CLIP for Few-shot Classificationcited by 355
  8. 2021NeRF in the Dark: High Dynamic Range View Synthesis from Noisy Raw Imagescited by 336
  9. 2021VL-Adapter: Parameter-Efficient Transfer Learning for Vision-and-Language Taskscited by 319
  10. 2018Unprocessing Images for Learned Raw Denoisingcited by 250
  11. 2020CycleISP: Real Image Restoration via Improved Data Synthesiscited by 212
  12. 2020A Physics-based Noise Formation Model for Extreme Low-light Raw Denoisingcited by 138
  13. 2020Replacing Mobile Camera ISP with a Single Deep Learning Modelcited by 108
  14. 2020Memory-Efficient Incremental Learning Through Feature Adaptationcited by 107
  15. 2021Invertible Image Signal Processingcited by 94
  16. 2018DeepISP: Towards Learning an End-to-End Image Processing Pipelinecited by 88
  17. 2022You Only Need 90K Parameters to Adapt Light: A Light Weight Transformer for Image Enhancement and Exposure Correctioncited by 81
  18. 2021Mobile Computational Photography: A Tourcited by 62
  19. 2022Multitask AET with Orthogonal Tangent Regularity for Dark Object Detectioncited by 59
  20. 2022Dancing under the stars: video denoising in starlightcited by 47
  21. 2021Learning RAW-to-sRGB Mappings with Inaccurately Aligned Supervisioncited by 43
  22. 2022Model-Based Image Signal Processors via Learnable Dictionariescited by 43
  23. 2017Dirty Pixels: Towards End-to-End Image Processing and Perceptioncited by 42
  24. 2019CameraNet: A Two-Stage Framework for Effective Camera ISP Learningcited by 38
  25. 2019What Else Can Fool Deep Learning? Addressing Color Constancy Errors on Deep Neural Network Performancecited by 37
  26. 2017Reconfiguring the Imaging Pipeline for Computer Visioncited by 32
  27. 2023NILUT: Conditional Neural Implicit 3D Lookup Tables for Image Enhancementcited by 31
  28. 2021ReconfigISP: Reconfigurable Camera Image Processing Pipelinecited by 30
  29. 2022DynamicISP: Dynamically Controlled Image Signal Processor for Image Recognitioncited by 23
  30. 2023ParamISP: Learned Forward and Inverse ISPs using Camera Parameterscited by 23
  31. 2019Automatic ISP image quality tuning using non-linear optimizationcited by 20
  32. 2019VisionISP: Repurposing the Image Signal Processor for Computer Vision Applicationscited by 18
  33. 2020Improved Handling of Motion Blur in Online Object Detectioncited by 18
  34. 2022Rawgment: Noise-Accounted RAW Augmentation Enables Recognition in a Wide Variety of Environmentscited by 18
  35. 2022Efficient Visual Computing with Camera RAW Snapshotscited by 18
  36. 2023Raw Image Reconstruction with Learned Compact Metadatacited by 18
  37. 2023Learning Degradation-Independent Representations for Camera ISP Pipelinescited by 11
  38. 2017Modelling the Scene Dependent Imaging in Cameras with a Deep Neural Networkcited by 8

50 most cited of 54 All 54 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 2; 2025: 9; 2026: 8.

19 papers.

Sort:

By area:

  1. 2025DifIISR: A Diffusion Model with Gradient Guidance for Infrared Image Super-Resolutioncited by 21
  2. 2024Towards RAW Object Detection in Diverse Conditionscited by 9
  3. 2025Dark-ISP: Enhancing RAW Image Processing for Low-Light Object Detectioncited by 5
  4. 2025Beyond RGB: Adaptive Parallel Processing for RAW Object Detectioncited by 4
  5. 2024RAWMamba: Unified sRGB-to-RAW De-rendering With State Space Modelcited by 3
  6. 2026RAWild: Sensor-Agnostic RAW Object Detection via Physics-Guided Curve and Grid Modelingcited by 3
  7. 2025SimROD: A Simple Baseline for Raw Object Detection with Global and Local Enhancementscited by 2
  8. 2025RAW-Adapter: Adapting Pre-trained Visual Model to Camera RAW Images and A Benchmarkcited by 2
  9. 2025Task-Aware Image Signal Processor for Advanced Visual Perceptioncited by 2
  10. 2026RAWDet-7: A Multi-Scenario Benchmark for Object Detection and Description on Quantized RAW Imagescited by 1
  11. 2026UniISP: A Unified ISP Framework for Both Human and Machine Visioncited by 1
  12. 2025SemiISP/SemiIE: Semi-Supervised Image Signal Processor and Image Enhancement Leveraging One-to-Many Mapping sRGB-to-RAWcited by 0
7 more
  1. 2025Spatial-Frequency Aware for Object Detection in RAW Imagecited by 0
  2. 2025Raw-JPEG Adapter: Efficient Raw Image Compression with JPEGcited by 0
  3. 2026MERIT: Multi-domain Efficient RAW Image Translationcited by 0
  4. 2026Making the Discrete Continuous: Synthetic RAW Augmentations for Fine-Grained Evaluation of Person Detection Performance in Low Lightcited by 0
  5. 2026FreqAdapt: Frequency-Adaptive Processing for RAW Object Detectioncited by 0
  6. 2026Real-Time Scene-Adaptive Tone Mapping for High-Dynamic Range Object Detectioncited by 0
  7. 2026FujinSplat: Seeing Through Smoke with RAW-Domain Gaussian Splattingcited by 0