End-to-End Denoising of Dark Burst Images Using Recurrent Fully Convolutional Networks
This addresses the problem of poor image quality in dim-light photography for users, offering an incremental improvement over existing burst-based methods.
The paper tackles denoising and color correction of burst images taken in extremely low-light conditions by proposing a recurrent fully convolutional network (RFCN) that maps raw burst images to sRGB outputs, achieving better results than state-of-the-art methods and demonstrating cross-camera applicability without fine-tuning.
When taking photos in dim-light environments, due to the small amount of light entering, the shot images are usually extremely dark, with a great deal of noise, and the color cannot reflect real-world color. Under this condition, the traditional methods used for single image denoising have always failed to be effective. One common idea is to take multiple frames of the same scene to enhance the signal-to-noise ratio. This paper proposes a recurrent fully convolutional network (RFCN) to process burst photos taken under extremely low-light conditions, and to obtain denoised images with improved brightness. Our model maps raw burst images directly to sRGB outputs, either to produce a best image or to generate a multi-frame denoised image sequence. This process has proven to be capable of accomplishing the low-level task of denoising, as well as the high-level task of color correction and enhancement, all of which is end-to-end processing through our network. Our method has achieved better results than state-of-the-art methods. In addition, we have applied the model trained by one type of camera without fine-tuning on photos captured by different cameras and have obtained similar end-to-end enhancements.