arXiv 2409.070402025-07-15cs.CVeess.IV

Retinex-RAWMamba：连接去马赛克与去噪以实现低照度RAW图像增强

Retinex-RAWMamba: Bridging Demosaicing and Denoising for Low-Light RAW Image Enhancement

Institute of Advanced Technology, University of Science and Technology of China（科学技术大学先进技术研究院）；School of Computer and Artificial Intelligence, Beijing Technology and Business University（北京科技与商务大学计算机与人工智能学院）；Institute of Artificial Intelligence, Hefei Comprehensive National Science Center（合肥综合性国家科学中心人工智能研究院）；University of Science and Technology of China（科学技术大学）；School of Automation, Northwestern Polytechnical University（西北工业大学自动化学院）

Xianmin Chen, Longfei Han, Peiliang Huang, Xiaoxu Feng, Dingwen Zhang, Junwei Han

DOI：: 10.1109/TCSVT.2025.3589476

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

针对低照度RAW图像跨域增强中单阶段去噪受限和两阶段颜色失真问题，提出RAWMamba方法，通过引入Retinex Decomposition Module解耦光照与反射率，连接去马赛克与去噪，在SID和MCR数据集上实现了最先进的跨域映射性能。

摘要：

低照度图像增强，特别是在从raw域映射到sRGB域的跨域任务中，仍然是一个重大挑战。近年来，人们开发了许多基于深度学习的方法来解决这一问题，并取得了可喜的成果。然而，单阶段方法试图统一两个域之间的复杂映射，导致去噪性能受限。相比之下，现有的两阶段方法通常忽略了图像信号处理（ISP）流水线中去马赛克的特性，导致在不同光照条件下（尤其是在低照度场景中）出现颜色失真。为了解决这些问题，我们提出了一种针对低照度RAW图像定制的基于Mamba的新方法，称为RAWMamba，以有效处理具有不同CFAs的raw图像。此外，我们引入了基于Retinex先验的Retinex Decomposition Module (RDM)，该模块将光照与反射率解耦，以促进更有效的去噪和自动非线性曝光校正，从而减少手动线性光照增强的影响。通过连接去马赛克与去噪，实现了对低照度RAW图像更好的增强。在公开数据集SID和MCR上进行的实验评估表明，我们提出的RAWMamba在跨域映射上实现了最先进的性能。代码可在https://github.com/Cynicarlos/RetinexRawMamba获取。

英文摘要：

Low-light image enhancement, particularly in cross-domain tasks such as mapping from the raw domain to the sRGB domain, remains a significant challenge. Many deep learning-based methods have been developed to address this issue and have shown promising results in recent years. However, single-stage methods, which attempt to unify the complex mapping across both domains, leading to limited denoising performance. In contrast, existing two-stage approaches typically overlook the characteristic of demosaicing within the Image Signal Processing (ISP) pipeline, leading to color distortions under varying lighting conditions, especially in low-light scenarios. To address these issues, we propose a novel Mamba-based method customized for low light RAW images, called RAWMamba, to effectively handle raw images with different CFAs. Furthermore, we introduce a Retinex Decomposition Module (RDM) grounded in Retinex prior, which decouples illumination from reflectance to facilitate more effective denoising and automatic non-linear exposure correction, reducing the effect of manual linear illumination enhancement. By bridging demosaicing and denoising, better enhancement for low light RAW images is achieved. Experimental evaluations conducted on public datasets SID and MCR demonstrate that our proposed RAWMamba achieves state-of-the-art performance on cross-domain mapping. The code is available at https://github.com/Cynicarlos/RetinexRawMamba.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。