Nautilus: Locality-aware Autoencoder for Scalable Mesh Generation

TL;DR

Nautilus is a novel locality-aware autoencoder that enables scalable, high-fidelity mesh generation by leveraging local properties of manifold meshes and a dual-stream point conditioning approach.

Contribution

It introduces a new tokenization algorithm and a dual-stream point conditioner to improve mesh generation scalability and structural fidelity.

Findings

Supports mesh generation with up to 5,000 faces.

Outperforms state-of-the-art methods in fidelity and scalability.

Achieves artist-like mesh quality with efficient representation.

Abstract

Triangle meshes are fundamental to 3D applications, enabling efficient modification and rasterization while maintaining compatibility with standard rendering pipelines. However, current automatic mesh generation methods typically rely on intermediate representations that lack the continuous surface quality inherent to meshes. Converting these representations into meshes produces dense, suboptimal outputs. Although recent autoregressive approaches demonstrate promise in directly modeling mesh vertices and faces, they are constrained by the limitation in face count, scalability, and structural fidelity. To address these challenges, we propose Nautilus, a locality-aware autoencoder for artist-like mesh generation that leverages the local properties of manifold meshes to achieve structural fidelity and efficient representation. Our approach introduces a novel tokenization algorithm that preserves face proximity relationships and compresses sequence length through locally shared vertices and edges, enabling the generation of meshes with an unprecedented scale of up to 5,000 faces. Furthermore, we develop a Dual-stream Point Conditioner that provides multi-scale geometric guidance, ensuring global consistency and local structural fidelity by capturing fine-grained geometric features. Extensive experiments demonstrate that Nautilus significantly outperforms state-of-the-art methods in both fidelity and scalability. The project page is at https://nautilusmeshgen.github.io.