论文标题
用于单图像的空间自适应网络
Spatial-Adaptive Network for Single Image Denoising
论文作者
论文摘要
先前的工作表明，卷积神经网络可以在图像降级任务中实现良好的性能。但是，受当地刚性卷积操作的限制，这些方法导致了过度厚度的工件。更深层次的网络结构可以减轻这些问题，但需要更多的计算开销。在本文中，我们提出了一个新型的空间自适应denoising网络（SADNET），以有效地消除单图像盲噪声。为了适应空间纹理和边缘的变化，我们设计了一个残留的空间自适应块。引入了可变形的卷积以采样用于加权的空间相关特征。引入了带有上下文块的编码器 - 编码器结构以捕获多尺度信息。通过从粗噪声到细噪声，可以获得高质量的无噪声图像。我们将我们的方法应用于合成和真实的嘈杂图像数据集。实验结果表明，我们的方法在定量和视觉上都可以超过最先进的去核方法。
Previous works have shown that convolutional neural networks can achieve good performance in image denoising tasks. However, limited by the local rigid convolutional operation, these methods lead to oversmoothing artifacts. A deeper network structure could alleviate these problems, but more computational overhead is needed. In this paper, we propose a novel spatial-adaptive denoising network (SADNet) for efficient single image blind noise removal. To adapt to changes in spatial textures and edges, we design a residual spatial-adaptive block. Deformable convolution is introduced to sample the spatially correlated features for weighting. An encoder-decoder structure with a context block is introduced to capture multiscale information. With noise removal from the coarse to fine, a high-quality noisefree image can be obtained. We apply our method to both synthetic and real noisy image datasets. The experimental results demonstrate that our method can surpass the state-of-the-art denoising methods both quantitatively and visually.
