Model-Blind Video Denoising via Frame-To-Frame Training

Thibaud Ehret, Axel Davy, Jean-Michel Morel, Gabriele Facciolo, Pablo Arias; The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019, pp. 11369-11378


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 video 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.

Related Material

[pdf] [supp]
author = {Ehret, Thibaud and Davy, Axel and Morel, Jean-Michel and Facciolo, Gabriele and Arias, Pablo},
title = {Model-Blind Video Denoising via Frame-To-Frame Training},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2019}