GCN-Denoiser:基于图卷积网络的网格去噪
GCN-Denoiser: Mesh Denoising with Graph Convolutional Networks
AI总结:
提出 GCN-Denoiser,利用三角网格图表示、对偶空间图卷积、静态/动态边卷积及级联 GCN 回归无噪声法向,在多类噪声数据上达到最优。
摘要:
本文提出 GCN-Denoiser,这是一种基于图卷积网络(GCN)的新型特征保持网格去噪方法。与以往利用手工设计表示或基于体素的表示进行特征学习的基于学习的网格去噪方法不同,我们的方法挖掘三角网格本身的结构,并引入一种图表示,随后在三角形的对偶空间中执行图卷积操作。我们表明,这种图表示能够自然捕捉几何特征,同时在训练和推理阶段都较为轻量。为促进有效的特征学习,网络同时利用静态和动态边卷积,从而既能从显式网格结构中学习信息,也能从未连接邻域之间潜在的隐式关系中学习信息。为更好地逼近未知噪声函数,我们引入级联优化范式,通过多个 GCN 逐步回归无噪声的面片法向。GCN-Denoiser 在多个噪声数据集上取得了新的最优结果,包括通常包含尖锐特征的 CAD 模型,以及使用不同设备采集、带有真实噪声的原始扫描模型。我们还创建了名为 PrintData 的新数据集,其中包含 20 个真实扫描及其对应的真值网格,以供研究社区使用。代码和数据可在 https://github.com/Jhonve/GCN-Denoiser 获取。
英文摘要:
In this paper, we present GCN-Denoiser, a novel feature-preserving mesh denoising method based on graph convolutional networks (GCNs). Unlike previous learning-based mesh denoising methods that exploit hand-crafted or voxel-based representations for feature learning, our method explores the structure of a triangular mesh itself and introduces a graph representation followed by graph convolution operations in the dual space of triangles. We show such a graph representation naturally captures the geometry features while being lightweight for both training and inference. To facilitate effective feature learning, our network exploits both static and dynamic edge convolutions, which allow us to learn information from both the explicit mesh structure and potential implicit relations among unconnected neighbors. To better approximate an unknown noise function, we introduce a cascaded optimization paradigm to progressively regress the noise-free facet normals with multiple GCNs. GCN-Denoiser achieves the new state-of-the-art results in multiple noise datasets, including CAD models often containing sharp features and raw scan models with real noise captured from different devices. We also create a new dataset called PrintData containing 20 real scans with their corresponding ground-truth meshes for the research community. Our code and data are available in https://github.com/Jhonve/GCN-Denoiser.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。