mlsanityData to 14 Oct 2026

Towards RAW Object Detection in Diverse Conditions

arXiv 2411.15678 ↗First posted 24 Nov 2024cs.CVcited by 9

Not on the map. Why?

Abstract (arXiv)

Existing object detection methods often consider sRGB input, which was compressed from RAW data using ISP originally designed for visualization. However, such compression might lose crucial information for detection, especially under complex light and weather conditions. We introduce the AODRaw dataset, which offers 7,785 high-resolution real RAW images with 135,601 annotated instances spanning 62 categories, capturing a broad range of indoor and outdoor scenes under 9 distinct light and weather conditions. Based on AODRaw that supports RAW and sRGB object detection, we provide a comprehensive benchmark for evaluating current detection methods. We find that sRGB pre-training constrains the potential of RAW object detection due to the domain gap between sRGB and RAW, prompting us to directly pre-train on the RAW domain. However, it is harder for RAW pre-training to learn rich representations than sRGB pre-training due to the camera noise. To assist RAW pre-training, we distill the knowledge from an off-the-shelf model pre-trained on the sRGB domain. As a result, we achieve substantial improvements under diverse and adverse conditions without relying on extra pre-processing modules. Code and dataset are available at https://github.com/lzyhha/AODRaw.

Key facts. Cited by 9 papers in the map (data through 14 Oct 2026). Builds on 32 of its 46 references that are in the map. First posted on arXiv 24 Nov 2024.

Builds on

32 of 46 references.

References · 32

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  3. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  4. 2015Distilling the Knowledge in a Neural Networkcited by 10,324
  5. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,639
  6. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
  7. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,403
  8. 2022A ConvNet for the 2020scited by 3,579
  9. 2020Deformable DETR: Deformable Transformers for End-to-End Object Detectioncited by 3,422
  10. 2019MMDetection: Open MMLab Detection Toolbox and Benchmarkcited by 1,385
  11. 2021YOLOX: Exceeding YOLO Series in 2021cited by 1,071
  12. 2020Sparse R-CNN: End-to-End Object Detection with Learnable Proposalscited by 495
20 more
  1. 2019Cascade R-CNN: High Quality Object Detection and Instance Segmentationcited by 429
  2. 2020Generalized Focal Loss: Learning Qualified and Distributed Bounding Boxes for Dense Object Detectioncited by 409
  3. 2018Unprocessing Images for Learned Raw Denoisingcited by 250
  4. 2022Visual Attention Networkcited by 210
  5. 2022Towards Large-Scale Small Object Detection: Survey and Benchmarkscited by 122
  6. 2022Contrastive Learning Rivals Masked Image Modeling in Fine-tuning via Feature Distillationcited by 93
  7. 2023Instance Segmentation in the Darkcited by 46
  8. 2017Dirty Pixels: Towards End-to-End Image Processing and Perceptioncited by 42
  9. 2023YOLO-MS: Rethinking Multi-Scale Representation Learning for Real-time Object Detectioncited by 33
  10. 2021ReconfigISP: Reconfigurable Camera Image Processing Pipelinecited by 30
  11. 2024Lighting Every Darkness with 3DGS: Fast Training and Real-Time Rendering for HDR View Synthesiscited by 27
  12. 2022DynamicISP: Dynamically Controlled Image Signal Processor for Image Recognitioncited by 23
  13. 2024RAW-Adapter: Adapting Pre-trained Visual Model to Camera RAW Imagescited by 19
  14. 2019VisionISP: Repurposing the Image Signal Processor for Computer Vision Applicationscited by 18
  15. 2022Efficient Visual Computing with Camera RAW Snapshotscited by 18
  16. 2024AdaptiveISP: Learning an Adaptive Image Signal Processor for Object Detectioncited by 18
  17. 2023Learning Degradation-Independent Representations for Camera ISP Pipelinescited by 11
  18. 2022Fewer is More: Efficient Object Detection in Large Aerial Imagescited by 6
  19. 2023DarkVision: A Benchmark for Low-light Image/Video Perceptioncited by 5
  20. 2023Make Explicit Calibration Implicit: Calibrate Denoiser Instead of the Noise Modelcited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 4; 2026: 5.

9 papers.

  1. 2025Depth Anything at Any Conditioncited by 12
  2. 2025DitHub: A Modular Framework for Incremental Open-Vocabulary Object Detectioncited by 3
  3. 2026RAWild: Sensor-Agnostic RAW Object Detection via Physics-Guided Curve and Grid Modelingcited by 3
  4. 2025RAW-Adapter: Adapting Pre-trained Visual Model to Camera RAW Images and A Benchmarkcited by 2
  5. 2025UNICE: Training A Universal Image Contrast Enhancercited by 0
  6. 2026SpiralDiff: Spiral Diffusion with LoRA for RGB-to-RAW Conversion Across Camerascited by 0
  7. 2026Allegory of the Cave: Measurement-Grounded Vision-Language Learningcited by 0
  8. 2026Making the Discrete Continuous: Synthetic RAW Augmentations for Fine-Grained Evaluation of Person Detection Performance in Low Lightcited by 0
  9. 2026FreqAdapt: Frequency-Adaptive Processing for RAW Object Detectioncited by 0