Neural Mesh Flow:基于同构流的三维流形网格生成
Neural Mesh Flow: 3D Manifold Mesh Generation via Diffeomorphic Flows
摘要:
网格是虚拟世界中三维实体的重要表示形式。渲染、模拟和3D打印等应用需要网格是多种多样的,这样它们就可以像它们所代表的真实对象一样与世界交互。现有方法生成的网格具有很高的几何精度,但流形性较差。在这项工作中,我们提出了神经网格流(NMF)生成两个流形网格亏格0形状。具体来说,NMF是一个形状自动编码器,由几个神经常微分方程(NODE)[1]块组成,通过渐进地变形球形网格来学习精确的网格几何形状。与最先进的方法相比,训练NMF更简单,因为它不需要任何显式的基于网格的正则化。实验结果表明,非负矩阵分解方法可以用于单视图网格重建、全局形状参数化、纹理映射、形状变形和对应等应用。重要的是,我们证明了使用NMF生成的流形网格更适合于基于基于物理的渲染和模拟。代码和数据已发布。
英文摘要:
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.
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。