In this paper, we present a powerful differentiable surface fitting technique to derive a compact surface representation for a given dense point cloud or mesh, with application in the domains of graphics and CAD/CAM. We have chosen the Loop subdivision surface, which in the limit yields the smooth surface underlying the point cloud, and can handle complex surface topology better than other popular compact representations, such as NURBS. The principal idea is to fit the Loop subdivision surface not directly to the point cloud, but to the IMLS (implicit moving least squares) surface defined over the point cloud. As both Loop subdivision and IMLS have analytical expressions, we are able to formulate the problem as an unconstrained minimization problem of a completely differentiable function that can be solved with standard numerical solvers. Differentiability enables us to integrate the subdivision surface into any deep learning method for point clouds or meshes. We demonstrate the versatility and potential of this approach by using it in conjunction with a differentiable renderer to robustly reconstruct compact surface representations of spatial-temporal sequences of dense meshes.
翻译:在本文中,我们展示了一种强大的、可区分的表面适应技术,为某个密度点云或网状形成一个紧凑的表面表层,在图形和 CAD/CAM 领域应用。我们选择了环形亚分割面,在有限范围内产生点云背后的光滑表面,并且能够比其他广受欢迎的缩压表层(如NURBS)更好地处理复杂的表面表层。主要的想法是,将环形亚分割面直接适应点云,而不是直接适应点云,而是适应点云上定义的IMLS(隐形移动最小方块)表面。由于环形小区和IMLS 都有分析表达方式,我们能够将问题发展成一个完全不同的功能的不受限制的最小化问题,而这种功能可以通过标准的数值解算来解决。差异使我们能够将亚形表面纳入任何关于点云或网状云的深层学习方法。我们用它与一个不同的变异的转化器一起,用它来强有力地重建高密度介层空间-时段序列的紧凑表层。