LoG3D: Ultra-High-Resolution 3D Shape Modeling via Local-to-Global Partitioning

TL;DR

LoG3D introduces a scalable, high-resolution 3D shape modeling framework using local-to-global partitioning of unsigned distance fields, achieving superior detail and flexibility over existing methods.

Contribution

The paper presents a novel UDF-based 3D VAE with a local-to-global architecture that enables ultra-high-resolution shape modeling up to 2048^3, overcoming previous resolution and complexity limitations.

Findings

Achieves state-of-the-art reconstruction accuracy.

Supports ultra-high resolutions up to 2048^3.

Produces smooth, detailed, and flexible 3D shapes.

Abstract

Generating high-fidelity 3D contents remains a fundamental challenge due to the complexity of representing arbitrary topologies-such as open surfaces and intricate internal structures-while preserving geometric details. Prevailing methods based on signed distance fields (SDFs) are hampered by costly watertight preprocessing and struggle with non-manifold geometries, while point-cloud representations often suffer from sampling artifacts and surface discontinuities. To overcome these limitations, we propose a novel 3D variational autoencoder (VAE) framework built upon unsigned distance fields (UDFs)-a more robust and computationally efficient representation that naturally handles complex and incomplete shapes. Our core innovation is a local-to-global (LoG) architecture that processes the UDF by partitioning it into uniform subvolumes, termed UBlocks. This architecture couples 3D convolutions for capturing local detail with sparse transformers for enforcing global coherence. A Pad-Average strategy further ensures smooth transitions at subvolume boundaries during reconstruction. This modular design enables seamless scaling to ultra-high resolutions up to $2048^3$-a regime previously unattainable for 3D VAEs. Experiments demonstrate state-of-the-art performance in both reconstruction accuracy and generative quality, yielding superior surface smoothness and geometric flexibility.