用新几何表示法生成高质量3D资产，支持真实材质渲染。
3DTopia-XL: Scaling High-quality 3D Asset Generation via Primitive Diffusion
- 用紧凑张量格式编码形状、颜色和材质信息。
- 生成高精度带真实材质的3D模型，速度与质量优于现有方法。
- 适合需要高保真3D内容的游戏/影视/设计行业使用。
各行业对高质量3D资产的需求日益增长，亟需高效自动化的内容生成方案。尽管3D生成模型取得进展，但优化速度慢、几何保真度低、缺乏物理渲染所需材质数据仍是难题。本文提出3DTopia-XL，一种可扩展的原生3D生成模型，采用新型基于图元的3D表示法PrimX，将详细形状、反照率和材质场编码为紧凑张量格式，支持高分辨率几何与物理渲染（PBR）资产建模。在此基础上，构建基于扩散变换器（DiT）的生成框架，包含图元块压缩与潜在图元扩散两部分。3DTopia-XL能从文本或视觉输入生成高质量3D资产。大量定性与定量实验表明，该模型在生成具有细粒度纹理与材质的3D资产方面显著优于现有方法，有效弥合了生成模型与真实应用间的质量差距。
原文摘要 · Abstract (English)
The increasing demand for high-quality 3D assets across various industries necessitates efficient and automated 3D content creation. Despite recent advancements in 3D generative models, existing methods still face challenges with optimization speed, geometric fidelity, and the lack of assets for physically based rendering (PBR). In this paper, we introduce 3DTopia-XL, a scalable native 3D generative model designed to overcome these limitations. 3DTopia-XL leverages a novel primitive-based 3D representation, PrimX, which encodes detailed shape, albedo, and material field into a compact tensorial format, facilitating the modeling of high-resolution geometry with PBR assets. On top of the novel representation, we propose a generative framework based on Diffusion Transformer (DiT), which comprises 1) Primitive Patch Compression, 2) and Latent Primitive Diffusion. 3DTopia-XL learns to generate high-quality 3D assets from textual or visual inputs. We conduct extensive qualitative and quantitative experiments to demonstrate that 3DTopia-XL significantly outperforms existing methods in generating high-quality 3D assets with fine-grained textures and materials, efficiently bridging the quality gap between generative models and real-world applications.
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。