Mesh Processing Non-Meshes via Neural Displacement Fields

TL;DR

This paper introduces a neural field approach that converts coarse mesh approximations into accurate surface representations, enabling efficient geometry processing and transmission for non-mesh surfaces.

Contribution

It presents a neural map that transforms coarse meshes into detailed surfaces, reducing data size and enabling fast geometry processing without traditional meshing.

Findings

Achieves compact representation of a few hundred kilobytes.

Enables fast extraction of meshes for shape analysis.

Compresses scalar fields for efficient data delivery.

Abstract

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.