Restoration and enhancement on low exposure raw images by joint demosaicing and denoising.

Restoring high quality images from raw data in low light is challenging due to various noises caused by limited photon count and complicated Image Signal Process (ISP). Although several restoration and enhancement approaches are proposed, they may fail in extreme conditions, such as imaging short exposure raw data. The first path-breaking attempt is to utilize the connection between a pair of short and long exposure raw data and outputs RGB images as the final results. However, the whole pipeline still suffers from some blurs and color distortion. To overcome those difficulties, we propose an end-to-end network that contains two effective subnets to joint demosaic and denoise low exposure raw images. While traditional ISP are difficult to image them in acceptable conditions, the short exposure raw images can be better restored and enhanced by our model. For denoising, the proposed Short2Long raw restoration subnet outputs pseudo long exposure raw data with little noisy points. Then for demosaicing, the proposed Color consistent RGB enhancement subnet generates corresponding RGB images with the desired attributes: sharpness, color vividness, good contrast and little noise. By training the network in an end-to-end manner, our method avoids additional tuning by experts. We conduct experiments to reveal good results on three raw data datasets. We also illustrate the effectiveness of each module and the well generalization ability of this model. • We propose a Short2Long raw restoration strategy to process low quality raw images and restore pseudo raw ones for the subsequent subnet. It extracts sufficient information and removes enough noisy points, thus mainly focuses on the denoising task. • We device a Color consistent RGB enhancement mechanism to rearrange raw images and generate the final RGB outputs. With the residual connection and channel-wise attention, it reconstructs the color spatial information and emphasizes more on the demosaicing task. • Both quantitative and qualitative experiments are conducted to demonstrate the superiority of our proposed method. Ablation studies prove the effectiveness of modules. We also illustrate its promising generalization ability on unseen raw data such as images from smartphones. [ABSTRACT FROM AUTHOR]