用局部注意力提升3D生成速度，6.7倍加速且保持高精度
Ultra3D: Efficient and High-Fidelity 3D Generation with Part Attention
- 分阶段生成：先粗略布局，再局部细化
- 引入部件注意力机制，计算量降低6.7倍
- 适合需要高效高质量3D建模的开发者
稀疏体素表示的进展显著提升了3D内容生成质量，支持高分辨率精细建模。但现有框架因两阶段扩散流程中注意力机制的二次复杂度，存在严重计算效率问题。本文提出Ultra3D，通过紧凑的VecSet表示在第一阶段高效生成粗略物体布局，减少令牌数量并加速体素坐标预测。第二阶段引入部件注意力（Part Attention），一种几何感知的局部注意力机制，将注意力计算限制在语义一致的部件区域内，保持结构连续性的同时避免不必要的全局注意力，实现高达6.7倍的潜在特征生成速度提升。为此构建可扩展的部件标注流水线，将原始网格转换为带部件标签的稀疏体素。大量实验表明，Ultra3D可在1024分辨率下支持高质量3D生成，在视觉保真度和用户偏好上达到当前最优水平。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。