Abstract. Deep convolutional neural networks (CNNs) have achieved considerable success with image denoising. However, they still lack consistent performance across different noise types and levels. We extend noise scenarios to four categories: Gaussian, random-impulse, salt-and-pepper, and Poisson. We also propose a multinoise-type blind denoising network (MBDNet) that solves the blind denoising task using a uniform deep CNN architecture. The network can be divided into two stages where a concise CNN is first used to estimate auxiliary noise-type and noise-level information. Estimation results are then integrated as additional channels of the noisy image and are fed to the subsequent denoising stage. A unique two-branch structure is further adopted in the residual denoising CNN, wherein a shallow branch predicts the filter-flow mask and adaptively adjusts the feature extraction of the parallel deep branch. Extensive experiments on synthetic noisy images validate the effectiveness of the noise-estimation and denoising subnetworks and show that MBDNet is highly competitive as compared to state-of-the-art methods in both denoising performance and model runtime.

中文翻译：

---

使用单个均匀深度卷积神经网络的多噪声型盲去噪

摘要。深度卷积神经网络 (CNN) 在图像去噪方面取得了相当大的成功。然而，它们在不同的噪音类型和水平上仍然缺乏一致的性能。我们将噪声场景扩展到四类：高斯、随机脉冲、椒盐和泊松。我们还提出了一种多噪声型盲去噪网络 (MBDNet)，它使用统一的深度 CNN 架构解决盲去噪任务。该网络可以分为两个阶段，首先使用简洁的 CNN 来估计辅助噪声类型和噪声级别信息。然后将估计结果整合为噪声图像的附加通道，并馈送到后续的去噪阶段。在残差去噪CNN中进一步采用了独特的二分支结构，其中浅分支预测滤波器流掩码并自适应调整并行深分支的特征提取。对合成噪声图像的大量实验验证了噪声估计和去噪子网络的有效性，并表明 MBDNet 在去噪性能和模型运行时与最先进的方法相比具有很强的竞争力。