MeshFeat: Multi-Resolution Features for Neural Fields on Meshes

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Mahajan, Mihir, Hofherr, Florian, Cremers, Daniel
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917726926143488
author Mahajan, Mihir
Hofherr, Florian
Cremers, Daniel
author_facet Mahajan, Mihir
Hofherr, Florian
Cremers, Daniel
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2407_13592
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle MeshFeat: Multi-Resolution Features for Neural Fields on Meshes
Mahajan, Mihir
Hofherr, Florian
Cremers, Daniel
Computer Vision and Pattern Recognition
Machine Learning
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.
title MeshFeat: Multi-Resolution Features for Neural Fields on Meshes
topic Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2407.13592