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. Based on the maximum a posterior (MAP) estimation framework and recent advances in deep learning, we present a novel deep MAP-based video denoising method named MAP-VDNet with adaptive temporal fusion and deep image prior. The proposed MAP-based VD algorithm allows computationally efficient untangling of motion estimation (frame alignment) and image restoration (denoising). To address the misalignment issue, we also present a robust multi-frame fusion strategy for predicting spatially varying fusion weights by a neural network. To facilitate end-to-end optimization, we unfold the proposed iterative MAP-based VD algorithm 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.

与图像去噪研究的成熟不同，视频去噪仍然是一个具有挑战性的问题。视频去噪 (VD) 问题核心的一个基本问题是如何有原则地利用视频帧中的时间冗余来有效去除噪声。基于最大后验 (MAP) 估计框架和深度学习的最新进展，我们提出了一种新的基于深度 MAP 的视频去噪方法，名为MAP-VDNet具有自适应时间融合和深度图像先验。所提出的基于 MAP 的 VD 算法允许在计算上有效地解开运动估计（帧对齐）和图像恢复（去噪）。为了解决错位问题，我们还提出了一种强大的多帧融合策略，用于通过神经网络预测空间变化的融合权重。为了促进端到端优化，我们将提出的基于迭代 MAP 的 VD 算法展开为一个名为MAP-VDNet的深度卷积网络。在三个流行的视频数据集上的大量实验结果表明，所提出的MAP-VDNet显着优于当前最先进的 VD 技术，如 ViDeNN 和 FastDVDnet。代码可在 https://see.xidian.edu.cn/faculty/wsdong/Projects/MAP-VDNet.htm 获得。