Hierarchical Neural Surfaces for 3D Mesh Compression

TL;DR

This paper introduces a hierarchical neural implicit representation for 3D mesh compression that efficiently encodes surface details, enabling real-time decoding with high quality and compact size.

Contribution

It presents a novel hierarchical INR method for compressing triangle meshes by encoding displacement fields on a spherical parameterization.

Findings

Achieves state-of-the-art compression quality for 3D meshes.

Supports real-time decoding at arbitrary resolutions.

Provides a hierarchical structure that captures coarse to fine details.

Abstract

Implicit Neural Representations (INRs) have been demonstrated to achieve state-of-the-art compression of a broad range of modalities such as images, videos, 3D surfaces, and audio. Most studies have focused on building neural counterparts of traditional implicit representations of 3D geometries, such as signed distance functions. However, the triangle mesh-based representation of geometry remains the most widely used representation in the industry, while building INRs capable of generating them has been sparsely studied. In this paper, we present a method for building compact INRs of zero-genus 3D manifolds. Our method relies on creating a spherical parameterization of a given 3D mesh - mapping the surface of a mesh to that of a unit sphere - then constructing an INR that encodes the displacement vector field defined continuously on its surface that regenerates the original shape. The compactness of our representation can be attributed to its hierarchical structure, wherein it first recovers the coarse structure of the encoded surface before adding high-frequency details to it. Once the INR is computed, 3D meshes of arbitrary resolution/connectivity can be decoded from it. The decoding can be performed in real time while achieving a state-of-the-art trade-off between reconstruction quality and the size of the compressed representations.