Hunyuan3D 2.5生成高保真细节3D资产，形状纹理均显著提升。
Hunyuan3D 2.5: Towards High-Fidelity 3D Assets Generation with Ultimate Details
- 分两阶段生成，引入新形状模型LATTICE，支持100亿参数
- 生成3D网格表面光滑，图像-3D对齐精准，接近手工制作水平
- 采用基于物理的渲染（PBR）多视角架构，端到端纹理质量领先
本文介绍Hunyuan3D 2.5，一套稳健的3D扩散模型，用于生成高保真、细节丰富的带纹理3D资产。该版本延续前代Hunyuan3D 2.0的两阶段流程，但在形状与纹理生成上均有显著提升。在形状生成方面，引入新的形状基础模型LATTICE，基于扩大规模的高质量数据集、模型尺寸与计算资源训练。最大模型达100亿参数，生成的3D形状锐利精细，图像-3D对齐精准，同时保持网格表面清洁光滑，大幅缩小生成与手工制作3D形状间的差距。在纹理生成方面，通过扩展自Hunyuan3D 2.0 Paint模型的新型多视图架构，集成基于物理的渲染（PBR）。大量评估表明，Hunyuan3D 2.5在形状生成与端到端纹理生成方面均显著优于此前方法。
原文摘要 · Abstract (English)
In this report, we present Hunyuan3D 2.5, a robust suite of 3D diffusion models aimed at generating high-fidelity and detailed textured 3D assets. Hunyuan3D 2.5 follows two-stages pipeline of its previous version Hunyuan3D 2.0, while demonstrating substantial advancements in both shape and texture generation. In terms of shape generation, we introduce a new shape foundation model -- LATTICE, which is trained with scaled high-quality datasets, model-size, and compute. Our largest model reaches 10B parameters and generates sharp and detailed 3D shape with precise image-3D following while keeping mesh surface clean and smooth, significantly closing the gap between generated and handcrafted 3D shapes. In terms of texture generation, it is upgraded with phyiscal-based rendering (PBR) via a novel multi-view architecture extended from Hunyuan3D 2.0 Paint model. Our extensive evaluation shows that Hunyuan3D 2.5 significantly outperforms previous methods in both shape and end-to-end texture generation.
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。