Nautilus: Locality-aware Autoencoder for Scalable Mesh Generation

2025-01-24

AI Summary

Existing automatic mesh generation methods struggle to simultaneously ensure surface continuity, structural fidelity, and scalability during the intermediate representation stage, often resulting in mesh distortion, suboptimal vertex density distribution, and limited capability for large-scale object processing. This paper proposes an end-to-end framework for high-quality triangular mesh generation. We introduce a novel local-aware tokenization algorithm that preserves face adjacency relationships to guarantee topological consistency; design a dual-stream point conditioner that jointly models global semantics and local geometry; and integrate a locality-aware autoencoder with multi-scale geometric guidance. Our method supports high-fidelity mesh synthesis with up to 5,000 faces, achieving significant improvements over state-of-the-art approaches in structural integrity, surface smoothness, and scalability. To our knowledge, this is the first method enabling artist-level quality, large-scale triangular mesh generation in a fully end-to-end manner.

Technology Category

• Natural Language Processing: Generation
• Machine Learning: Deep Generative Models & Autoencoders
• Computer Vision: Diffusion Models for Vision

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies
• Web Mining and Content Analysis: Web data quality in the era of algorithmically-generated content

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.

Problem

• Smooth Surface Maintenance
• Optimal Mesh Density
• Large-scale Object Processing

Innovation

• Nautilus Autoencoder
• Dual-Stream Point Conditioner
• Highly Detailed Mesh Generation