MeshFeat: Multi-Resolution Features for Neural Fields on Meshes

TL;DR

MeshFeat introduces a multi-resolution feature encoding on meshes that enables faster neural field inference while maintaining quality, especially suited for deforming meshes and animation tasks.

Contribution

The paper proposes MeshFeat, a novel multi-resolution feature encoding tailored for meshes, improving inference speed and suitability for deforming objects.

Findings

Significant speed-up over previous methods

Maintains comparable reconstruction quality

Effective for deforming meshes and animation

Abstract

Parametric feature grid encodings have gained significant attention as an encoding approach for neural fields since they allow for much smaller MLPs, which significantly decreases the inference time of the models. In this work, we propose MeshFeat, a parametric feature encoding tailored to meshes, for which we adapt the idea of multi-resolution feature grids from Euclidean space. We start from the structure provided by the given vertex topology and use a mesh simplification algorithm to construct a multi-resolution feature representation directly on the mesh. The approach allows the usage of small MLPs for neural fields on meshes, and we show a significant speed-up compared to previous representations while maintaining comparable reconstruction quality for texture reconstruction and BRDF representation. Given its intrinsic coupling to the vertices, the method is particularly well-suited for representations on deforming meshes, making it a good fit for object animation.