Ultra3D: Efficient and High-Fidelity 3D Generation with Part Attention

TL;DR

Ultra3D introduces a fast, high-fidelity 3D generation framework that uses part-aware attention and efficient representations to significantly reduce computation while maintaining quality.

Contribution

It proposes Part Attention and VecSet for efficient, high-resolution 3D generation, reducing complexity and accelerating voxel modeling without quality loss.

Findings

Achieves up to 6.7x speed-up in latent generation.

Supports high-resolution 1024 3D generation.

Outperforms previous methods in visual fidelity and user preference.

Abstract

Recent advances in sparse voxel representations have significantly improved the quality of 3D content generation, enabling high-resolution modeling with fine-grained geometry. However, existing frameworks suffer from severe computational inefficiencies due to the quadratic complexity of attention mechanisms in their two-stage diffusion pipelines. In this work, we propose Ultra3D, an efficient 3D generation framework that significantly accelerates sparse voxel modeling without compromising quality. Our method leverages the compact VecSet representation to efficiently generate a coarse object layout in the first stage, reducing token count and accelerating voxel coordinate prediction. To refine per-voxel latent features in the second stage, we introduce Part Attention, a geometry-aware localized attention mechanism that restricts attention computation within semantically consistent part regions. This design preserves structural continuity while avoiding unnecessary global attention, achieving up to 6.7x speed-up in latent generation. To support this mechanism, we construct a scalable part annotation pipeline that converts raw meshes into part-labeled sparse voxels. Extensive experiments demonstrate that Ultra3D supports high-resolution 3D generation at 1024 resolution and achieves state-of-the-art performance in both visual fidelity and user preference.