This article presents a deep normal filtering network, called DNF-Net, for mesh denoising. To better capture local geometry, our network processes the mesh in terms of local patches extracted from the mesh. Overall, DNF-Net is an end-to-end network that takes patches of facet normals as inputs and directly outputs the corresponding denoised facet normals of the patches. In this way, we can reconstruct the geometry from the denoised normals with feature preservation. Besides the overall network architecture, our contributions include a novel multi-scale feature embedding unit, a residual learning strategy to remove noise, and a deeply-supervised joint loss function. Compared with the recent data-driven works on mesh denoising, DNF-Net does not require manual input to extract features and better utilizes the training data to enhance its denoising performance. Finally, we present comprehensive experiments to evaluate our method and demonstrate its superiority over the state of the art on both synthetic and real-scanned meshes.

中文翻译：

---

DNF-Net：用于网格去噪的深度正态滤波网络


本文提出了一种深度法线过滤网络，称为 DNF-Net，用于网格去噪。为了更好地捕获局部几何形状，我们的网络根据从网格中提取的局部补丁来处理网格。总的来说，DNF-Net是一个端到端的网络，它将小面法线的补丁作为输入，并直接输出补丁对应的去噪后的小面法线。通过这种方式，我们可以通过保留特征的去噪法线重建几何形状。除了整体网络架构之外，我们的贡献还包括新颖的多尺度特征嵌入单元、去除噪声的残差学习策略以及深度监督的联合损失函数。与最近的数据驱动的网格去噪工作相比，DNF-Net不需要手动输入来提取特征，并且更好地利用训练数据来增强其去噪性能。最后，我们提出了全面的实验来评估我们的方法，并证明其在合成和真实扫描网格上相对于现有技术的优越性。