Dark-ISP: Enhancing RAW Image Processing for Low-Light Object Detection
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866916946318983168 |
|---|---|
| author | Guo, Jiasheng Gao, Xin Yan, Yuxiang Li, Guanghao Pu, Jian |
| author_facet | Guo, Jiasheng Gao, Xin Yan, Yuxiang Li, Guanghao Pu, Jian |
| contents | Low-light Object detection is crucial for many real-world applications but remains challenging due to degraded image quality. While recent studies have shown that RAW images offer superior potential over RGB images, existing approaches either use RAW-RGB images with information loss or employ complex frameworks. To address these, we propose a lightweight and self-adaptive Image Signal Processing (ISP) plugin, Dark-ISP, which directly processes Bayer RAW images in dark environments, enabling seamless end-to-end training for object detection. Our key innovations are: (1) We deconstruct conventional ISP pipelines into sequential linear (sensor calibration) and nonlinear (tone mapping) sub-modules, recasting them as differentiable components optimized through task-driven losses. Each module is equipped with content-aware adaptability and physics-informed priors, enabling automatic RAW-to-RGB conversion aligned with detection objectives. (2) By exploiting the ISP pipeline's intrinsic cascade structure, we devise a Self-Boost mechanism that facilitates cooperation between sub-modules. Through extensive experiments on three RAW image datasets, we demonstrate that our method outperforms state-of-the-art RGB- and RAW-based detection approaches, achieving superior results with minimal parameters in challenging low-light environments. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_09183 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Dark-ISP: Enhancing RAW Image Processing for Low-Light Object Detection Guo, Jiasheng Gao, Xin Yan, Yuxiang Li, Guanghao Pu, Jian Computer Vision and Pattern Recognition Artificial Intelligence Low-light Object detection is crucial for many real-world applications but remains challenging due to degraded image quality. While recent studies have shown that RAW images offer superior potential over RGB images, existing approaches either use RAW-RGB images with information loss or employ complex frameworks. To address these, we propose a lightweight and self-adaptive Image Signal Processing (ISP) plugin, Dark-ISP, which directly processes Bayer RAW images in dark environments, enabling seamless end-to-end training for object detection. Our key innovations are: (1) We deconstruct conventional ISP pipelines into sequential linear (sensor calibration) and nonlinear (tone mapping) sub-modules, recasting them as differentiable components optimized through task-driven losses. Each module is equipped with content-aware adaptability and physics-informed priors, enabling automatic RAW-to-RGB conversion aligned with detection objectives. (2) By exploiting the ISP pipeline's intrinsic cascade structure, we devise a Self-Boost mechanism that facilitates cooperation between sub-modules. Through extensive experiments on three RAW image datasets, we demonstrate that our method outperforms state-of-the-art RGB- and RAW-based detection approaches, achieving superior results with minimal parameters in challenging low-light environments. |
| title | Dark-ISP: Enhancing RAW Image Processing for Low-Light Object Detection |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2509.09183 |