论文标题
神经网格流量：3D歧管网格通过差异流生成
Neural Mesh Flow: 3D Manifold Mesh Generation via Diffeomorphic Flows
论文作者
论文摘要
网格是虚拟世界中物理3D实体的重要表示。渲染，仿真和3D打印等应用程序需要将网格流到流动状态，以便它们可以像其代表的真实对象一样与世界交互。先前的方法生成具有良好几何精度的网格，但多种多样。在这项工作中，我们建议神经网格流（NMF）生成属-0形状的两脉络网。具体而言，NMF是一个形状自动编码器，由几个神经普通微分方程（节点）[1]块组成，通过逐渐变形球形网格来学习准确的网格几何形状。与最先进的方法相比，训练NMF更简单，因为它不需要任何明确的基于网格的正规化。我们的实验表明，NMF促进了几种应用，例如单视网状重建，全局形状参数化，纹理映射，形状变形和对应关系。重要的是，我们证明了使用NMF生成的歧管网格非常适合基于物理的渲染和仿真。代码和数据已发布。
Meshes are important representations of physical 3D entities in the virtual world. Applications like rendering, simulations and 3D printing require meshes to be manifold so that they can interact with the world like the real objects they represent. Prior methods generate meshes with great geometric accuracy but poor manifoldness. In this work, we propose Neural Mesh Flow (NMF) to generate two-manifold meshes for genus-0 shapes. Specifically, NMF is a shape auto-encoder consisting of several Neural Ordinary Differential Equation (NODE)[1] blocks that learn accurate mesh geometry by progressively deforming a spherical mesh. Training NMF is simpler compared to state-of-the-art methods since it does not require any explicit mesh-based regularization. Our experiments demonstrate that NMF facilitates several applications such as single-view mesh reconstruction, global shape parameterization, texture mapping, shape deformation and correspondence. Importantly, we demonstrate that manifold meshes generated using NMF are better-suited for physically-based rendering and simulation. Code and data are released.
