triangle meshes remain the most popular data representation for surface
geometry. This ubiquitous representation is essentially a hybrid one that
decouples continuous vertex locations from the discrete topological
triangulation. Unfortunately, the combinatorial nature of the triangulat
本文介绍一种基于 Deep Signed Distance Function 的不可微分网格表述方法 MeshSDF，通过推理隐式场的扰动如何影响局部表面几何，最终不限制分辨率和拓扑结构地将 Deep Implicit Field 显式地表示成一个可微分的网格形状，该方法在单视角重建和基于物理的形状优化方面优于现有技术。