Moir\'e patterns frequently appear when capturing screens with smartphones or cameras, potentially compromising image quality. Previous studies suggest that moir\'e pattern elimination in the RAW domain offers greater efficiency compared to demoir\'eing in the sRGB domain. Nevertheless, relying solely on raw data for image demoir\'eing is insufficient in mitigating color cast due to the absence of essential information required for color correction by the Image Signal Processor (ISP). In this paper, we propose perform Image Demoir\'eing concurrently utilizing both RAW and sRGB data (RRID), which is readily accessible in both smartphones and digital cameras. We develop Skip-Connection-based Demoir\'eing Module (SCDM) with specific modules embeded in skip-connections for the efficient and effective demoir\'eing of RAW and sRGB features, respectively. Subsequently, we propose RGB Guided Image Signal Processor (RGISP) to incorporate color information from coarsely demoir\'ed sRGB features during the ISP stage, assisting the process of color recovery. Extensive experiments demonstrate that our RRID outperforms state-of-the-art approaches by 0.62dB in PSNR and 0.003 in SSIM, exhibiting superior performance both in moir\'e pattern removal and color cast correction.

翻译：在通过智能手机或相机拍摄屏幕时，摩尔纹图案频繁出现，可能损害图像质量。先前研究表明，在RAW域中消除摩尔纹比在sRGB域中进行去摩尔纹更高效。然而，仅依赖原始数据进行图像去摩尔纹不足以缓解色偏问题，因为图像信号处理器（ISP）进行色彩校正所需的必要信息缺失。本文提出同时利用RAW和sRGB数据（RRID）实现图像去摩尔纹，这两种数据在智能手机和数码相机中均可直接获取。我们开发了基于跳跃连接的去摩尔纹模块（SCDM），在跳跃连接中嵌入特定模块，分别高效处理RAW和sRGB特征的去摩尔纹任务。随后，我们提出RGB引导的图像信号处理器（RGISP），在ISP阶段引入已初步去摩尔纹的sRGB特征中的色彩信息，辅助色彩恢复过程。大量实验表明，我们的RRID方法在PSNR上提升0.62dB，在SSIM上提升0.003，优于现有最先进方法，在去除摩尔纹和校正色偏方面均表现出卓越性能。