Mesh Density Adaptation for Template-based Shape Reconstruction

TL;DR

This paper introduces a mesh density adaptation technique that improves 3D shape reconstruction by increasing vertex density near complex details, leading to more accurate results in inverse rendering and surface registration.

Contribution

It presents a novel mesh density adaptation energy that enhances vertex density in critical regions, addressing under-sampling issues in template-based shape reconstruction.

Findings

Improved reconstruction accuracy with density adaptation.

Effective in inverse rendering and non-rigid surface registration.

Outperforms methods without density control.

Abstract

In 3D shape reconstruction based on template mesh deformation, a regularization, such as smoothness energy, is employed to guide the reconstruction into a desirable direction. In this paper, we highlight an often overlooked property in the regularization: the vertex density in the mesh. Without careful control on the density, the reconstruction may suffer from under-sampling of vertices near shape details. We propose a novel mesh density adaptation method to resolve the under-sampling problem. Our mesh density adaptation energy increases the density of vertices near complex structures via deformation to help reconstruction of shape details. We demonstrate the usability and performance of mesh density adaptation with two tasks, inverse rendering and non-rigid surface registration. Our method produces more accurate reconstruction results compared to the cases without mesh density adaptation.