Data

Tools

Indexes

Applications

Experiments

Open Source Science

https://github.com/cuiziteng/eccv_raw_adapter

📷 [ECCV 2024] RAW-Adapter: Adapting Pre-trained Visual Model to Camera RAW Images

https://github.com/cuiziteng/eccv_raw_adapter

Science Score: 36.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • â—‹
    CITATION.cff file
  • ✓
    codemeta.json file
    Found codemeta.json file
  • ✓
    .zenodo.json file
    Found .zenodo.json file
  • â—‹
    DOI references
  • ✓
    Academic publication links
    Links to: arxiv.org
  • â—‹
    Academic email domains
  • â—‹
    Institutional organization owner
  • â—‹
    JOSS paper metadata
  • â—‹
    Scientific vocabulary similarity
    Low similarity (15.2%) to scientific vocabulary

Keywords

computational-photography eccv eccv2024 exposure-correction isp low-level-vision low-light-vision
Last synced: 6 months ago · JSON representation

Repository

📷 [ECCV 2024] RAW-Adapter: Adapting Pre-trained Visual Model to Camera RAW Images

Basic Info
  • Host: GitHub
  • Owner: cuiziteng
  • License: mit
  • Language: Jupyter Notebook
  • Default Branch: main
  • Homepage:
  • Size: 18.9 MB
Statistics
  • Stars: 72
  • Watchers: 5
  • Forks: 5
  • Open Issues: 1
  • Releases: 3
Topics
computational-photography eccv eccv2024 exposure-correction isp low-level-vision low-light-vision
Created over 1 year ago · Last pushed 10 months ago
Metadata Files
Readme License

README.md

[ECCV 2024] RAW-Adapter: Adapting Pre-trained Visual Model to Camera RAW Images (Paper) (Website) (Zhihu中文解读)

Ziteng Cui1, Tatsuya Harada1,2.

1.The University of Tokyo, 2.RIKEN AIP


2025.03.24 : An extension of RAW-Adapter is available at arxiv, we propose RAW-Bench (including 17 kinds of RAW-based common corruptions), and will release it soon !

2024.11.04: Fix some config problems (path) in detection part.

2024.08.26 : Upload code of our paper.

2024.07.04 : Paper accepted by ECCV 2024 !

🚀: Abstract

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 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.

(a). An overview of basic image signal processor (ISP) pipeline. (b). ISP and current visual model have different objectives. (c) Previous methods optimize ISP with down-stream visual model. (d) Our proposed RAW-Adapter.

Usage:

For object detection part:

cd mmdetection_github

For semantic segmentation part:

cd mmsegmentation_github

Citation:

If you use our dataset or find our work useful in your project, please consider to cite our paper, thx ~

@inproceedings{raw_adapter, title = {RAW-Adapter: Adapting Pretrained Visual Model to Camera RAW Images}, author = {Cui, Ziteng and Harada, Tatsuya}, booktitle={ECCV}, year={2024} }

Owner

  • Name: Cui Ziteng
  • Login: cuiziteng
  • Kind: user
  • Location: cui@mi.t.u-tokyo.ac.jp
  • Company: UTokyo Ph.D student (D1)

Hi, I'm interest in computational photography, as well as vision robustness~

GitHub Events

Total
  • Issues event: 18
  • Watch event: 29
  • Issue comment event: 25
  • Push event: 26
  • Fork event: 2
Last Year
  • Issues event: 18
  • Watch event: 29
  • Issue comment event: 25
  • Push event: 26
  • Fork event: 2

Issues and Pull Requests

Last synced: 6 months ago

All Time
  • Total issues: 7
  • Total pull requests: 0
  • Average time to close issues: 25 days
  • Average time to close pull requests: N/A
  • Total issue authors: 6
  • Total pull request authors: 0
  • Average comments per issue: 1.43
  • Average comments per pull request: 0
  • Merged pull requests: 0
  • Bot issues: 0
  • Bot pull requests: 0
Past Year
  • Issues: 7
  • Pull requests: 0
  • Average time to close issues: 25 days
  • Average time to close pull requests: N/A
  • Issue authors: 6
  • Pull request authors: 0
  • Average comments per issue: 1.43
  • Average comments per pull request: 0
  • Merged pull requests: 0
  • Bot issues: 0
  • Bot pull requests: 0
View more stats
Top Authors
Issue Authors
  • xinzwang (2)
  • LeonSakura (1)
  • heart-du (1)
  • ocean146 (1)
  • openAI-1 (1)
  • Eric-yuuki (1)
  • YuenFuiLau (1)
  • Chegva (1)
  • XiaMu799 (1)
  • linjunhe111 (1)
Pull Request Authors
Top Labels
Issue Labels
Pull Request Labels