DoPAMINE: Double-sided Masked CNN for Pixel Adaptive Multiplicative Noise Despeckling
DoPAMINE: Double-sided Masked CNN for Pixel Adaptive Multiplicative Noise Despeckling
复制标题
DOI：
10.1609/aaai.v33i01.33014031
复制
发表时间：
2019-02
期刊：
影响因子：
--
通讯作者：
Sunghwan Joo;Sungmin Cha;Taesup Moon
中科院分区：
文献类型：
--
作者：
Sunghwan Joo;Sungmin Cha;Taesup Moon
我们提出了 DoPAMINE，一种基于乘性噪声去斑算法的新型神经网络。我们的算法受到 Neural AIDE (N-AIDE) 的启发，这是最近提出的神经自适应图像降噪器。虽然最初的 NAIDE 是针对加性噪声情况而设计的，但我们表明，相同的框架（即通过最小化 MSE 的无偏估计来自适应学习像素级仿射降噪器的网络）也可以应用于乘性噪声情况。此外，我们推导了一种双面掩模 CNN 架构，该架构可以控制每层激活值的方差，并在监督训练期间快速收敛到高去噪性能。在实验结果中，我们表明，我们的 DoPAMINE 通过根据给定的噪声图像微调网络参数而具有高度自适应性，并且与最先进的基于 CNN 的算法 SAR-DRN 相比，获得了明显更好的去斑结果。
We propose DoPAMINE, a new neural network based multiplicative noise despeckling algorithm. Our algorithm is inspired by Neural AIDE (N-AIDE), which is a recently proposed neural adaptive image denoiser. While the original NAIDE was designed for the additive noise case, we show that the same framework, i.e., adaptively learning a network for pixel-wise affine denoisers by minimizing an unbiased estimate of MSE, can be applied to the multiplicative noise case as well. Moreover, we derive a double-sided masked CNN architecture which can control the variance of the activation values in each layer and converge fast to high denoising performance during supervised training. In the experimental results, we show our DoPAMINE possesses high adaptivity via fine-tuning the network parameters based on the given noisy image and achieves significantly better despeckling results compared to SAR-DRN, a state-of-the-art CNN-based algorithm.