U.S. flag

An official website of the United States government, Department of Justice.

Democrats have shut down the government. Department of Justice websites are not currently regularly updated. Please refer to the Department of Justice’s contingency plan for more information.

Deep Maximum a Posterior Estimator for Video Denoising

NCJ Number
302843
Journal
International Journal of Computer Vision Volume: 129 Dated: 2021 Pages: 2874-2845
Date Published
August 2021
Annotation

Based on the maximum a posterior (MAP) estimation framework and recent advances in deep learning, this article presents a novel deep MAP-based video denoising method named MAP-VDNet with adaptive temporal fusion and deep image prior.

Abstract

Unlike the maturity of image denoising research, video denoising has remained a challenging problem. A fundamental issue at the core of the video denoising (VD) problem is how to efficiently remove noise by exploiting temporal redundancy in video frames in a principled manner. The proposed MAP-based VD algorithm enables computationally efficient untangling of motion estimation (frame alignment) and image restoration (denoising). To address the misalignment issue, this article also presents a robust multi-frame fusion strategy for predicting spatially varying fusion weights by a neural network. To facilitate end-to-end optimization, the proposed iterative MAP-based VD algorithm unfolds into a deep convolutional network named MAP-VDNet. Extensive experimental results on three popular video datasets have shown that the proposed MAP-VDNet significantly outperforms current state-of-the-art VD techniques such as ViDeNN and FastDVDnet. The code is available at https://see.xidian.edu.cn/faculty/wsdong/Projects/MAP-VDNet.htm. (publisher abstract modified)

Date Published: August 1, 2021