DarkDiff: Advancing Low-Light Raw Enhancement by Retasking Diffusion Models for Camera ISP
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_ | 1866908384363544576 |
|---|---|
| author | Zheng, Amber Yijia Zhang, Yu Hu, Jun Yeh, Raymond A. Chen, Chen |
| author_facet | Zheng, Amber Yijia Zhang, Yu Hu, Jun Yeh, Raymond A. Chen, Chen |
| contents | High-quality photography in extreme low-light conditions is challenging but impactful for digital cameras. With advanced computing hardware, traditional camera image signal processor (ISP) algorithms are gradually being replaced by efficient deep networks that enhance noisy raw images more intelligently. However, existing regression-based models often minimize pixel errors and result in oversmoothing of low-light photos or deep shadows. Recent work has attempted to address this limitation by training a diffusion model from scratch, yet those models still struggle to recover sharp image details and accurate colors. We introduce a novel framework to enhance low-light raw images by retasking pre-trained generative diffusion models with the camera ISP. Extensive experiments demonstrate that our method outperforms the state-of-the-art in perceptual quality across three challenging low-light raw image benchmarks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_23743 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | DarkDiff: Advancing Low-Light Raw Enhancement by Retasking Diffusion Models for Camera ISP Zheng, Amber Yijia Zhang, Yu Hu, Jun Yeh, Raymond A. Chen, Chen Computer Vision and Pattern Recognition Image and Video Processing High-quality photography in extreme low-light conditions is challenging but impactful for digital cameras. With advanced computing hardware, traditional camera image signal processor (ISP) algorithms are gradually being replaced by efficient deep networks that enhance noisy raw images more intelligently. However, existing regression-based models often minimize pixel errors and result in oversmoothing of low-light photos or deep shadows. Recent work has attempted to address this limitation by training a diffusion model from scratch, yet those models still struggle to recover sharp image details and accurate colors. We introduce a novel framework to enhance low-light raw images by retasking pre-trained generative diffusion models with the camera ISP. Extensive experiments demonstrate that our method outperforms the state-of-the-art in perceptual quality across three challenging low-light raw image benchmarks. |
| title | DarkDiff: Advancing Low-Light Raw Enhancement by Retasking Diffusion Models for Camera ISP |
| topic | Computer Vision and Pattern Recognition Image and Video Processing |
| url | https://arxiv.org/abs/2505.23743 |