Model-blind Video Denoising Via Frame-to-frame Training [article]

Thibaud Ehret, Axel Davy, Jean-Michel Morel, Gabriele Facciolo, Pablo Arias
2020 arXiv   pre-print
Modeling the processing chain that has produced a video is a difficult reverse engineering task, even when the camera is available. This makes model based video processing a still more complex task. In this paper we propose a fully blind video denoising method, with two versions off-line and on-line. This is achieved by fine-tuning a pre-trained AWGN denoising network to the video with a novel frame-to-frame training strategy. Our denoiser can be used without knowledge of the origin of the
more » ... or burst and the post processing steps applied from the camera sensor. The on-line process only requires a couple of frames before achieving visually-pleasing results for a wide range of perturbations. It nonetheless reaches state of the art performance for standard Gaussian noise, and can be used off-line with still better performance.
arXiv:1811.12766v3 fatcat:i3y3zgh7ezggph3u7yzlpqwcpa