Mesh Processing Non-Meshes via Neural Displacement Fields

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Noma, Yuta, Wang, Zhecheng, Liu, Chenxi, Singh, Karan, Jacobson, Alec
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866913995260166144
author Noma, Yuta
Wang, Zhecheng
Liu, Chenxi
Singh, Karan
Jacobson, Alec
author_facet Noma, Yuta
Wang, Zhecheng
Liu, Chenxi
Singh, Karan
Jacobson, Alec
contents Mesh processing pipelines are mature, but adapting them to newer non-mesh surface representations -- which enable fast rendering with compact file size -- requires costly meshing or transmitting bulky meshes, negating their core benefits for streaming applications. We present a compact neural field that enables common geometry processing tasks across diverse surface representations. Given an input surface, our method learns a neural map from its coarse mesh approximation to the surface. The full representation totals only a few hundred kilobytes, making it ideal for lightweight transmission. Our method enables fast extraction of manifold and Delaunay meshes for intrinsic shape analysis, and compresses scalar fields for efficient delivery of costly precomputed results. Experiments and applications show that our fast, compact, and accurate approach opens up new possibilities for interactive geometry processing.
format Preprint
id arxiv_https___arxiv_org_abs_2508_12179
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Mesh Processing Non-Meshes via Neural Displacement Fields
Noma, Yuta
Wang, Zhecheng
Liu, Chenxi
Singh, Karan
Jacobson, Alec
Graphics
Mesh processing pipelines are mature, but adapting them to newer non-mesh surface representations -- which enable fast rendering with compact file size -- requires costly meshing or transmitting bulky meshes, negating their core benefits for streaming applications. We present a compact neural field that enables common geometry processing tasks across diverse surface representations. Given an input surface, our method learns a neural map from its coarse mesh approximation to the surface. The full representation totals only a few hundred kilobytes, making it ideal for lightweight transmission. Our method enables fast extraction of manifold and Delaunay meshes for intrinsic shape analysis, and compresses scalar fields for efficient delivery of costly precomputed results. Experiments and applications show that our fast, compact, and accurate approach opens up new possibilities for interactive geometry processing.
title Mesh Processing Non-Meshes via Neural Displacement Fields
topic Graphics
url https://arxiv.org/abs/2508.12179