【摘要】 深度学习在计算机视觉领域应用非常成功，促进了图像降噪和多帧图像降噪领域的快速发展。本文针对多帧图像降噪问题，提出一种从多帧噪声图像中恢复清晰图像的方法。该方法结合BM3D（块匹配和三维滤波，block-matching and 3D filtering）算法和卷积神经网络（CNN）模型完成多帧图像降噪任务。该CNN模型基于分治法的思想设计。首先，用BM3D算法处理带噪声的多帧图像。然后，将预处理后的图像和原始噪声图像分别输入CNN模型的两个并行分支。最后，用一个轻量级CNN模块融合两个分支的输出得到最终图像估计。与以往研究不同，我们对CNN中两个并行分支分配了不同约束函数——信号约束和噪声约束，以提升模型提取不同特征的能力。此外，引入图像块匹配策略解决帧不对齐问题。在合成和真实噪声图像上的实验结果表明，该算法与其他算法相比具有一定竞争力。更多还原

【Abstract】 Deep learning has proven to be an effective mechanism for computer vision tasks, especially for image denoising and burst image denoising. In this paper, we focus on solving the burst image denoising problem and aim to generate a single clean image from a burst of noisy images. We propose to combine the power of block matching and3 D filtering(BM3 D) and a convolutional neural network(CNN) for burst image denoising. In particular, we design a CNN with a divide-and-conquer strategy. First, we employ BM3 D to preprocess the noisy burst images. Then,the preprocessed images and noisy images are fed separately into two parallel CNN branches. The two branches produce somewhat different results. Finally, we use a light CNN block to combine the two outputs. In addition, we improve the performance by optimizing the two branches using two different constraints: a signal constraint and a noise constraint. One maps a clean signal, and the other maps the noise distribution. In addition, we adopt block matching in the network to avoid frame misalignment. Experimental results on synthetic and real noisy images show that our algorithm is competitive with other algorithms.更多还原