用分步生成结构的Transformer，让3D可动模型更真实、更紧凑。
MeshArt: Generating Articulated Meshes with Structure-Guided Transformers
- 分两阶段生成：先定骨架结构，再依结构逐部分生成网格。
- 结构覆盖率达57.1%提升，网格生成FID降低209点。
- 适合需要高质量可动3D模型的虚拟资产开发者。
可动3D物体生成对创建真实、功能性和可交互的虚拟资产至关重要。我们提出MeshArt，一种基于分层Transformer的方法，用于生成具有清晰紧凑几何结构的可动3D网格，接近人工设计的3D模型。该方法采用分部件两阶段生成策略：首先生成高阶的、与关节相关的对象结构；随后，基于此结构信息，逐部分合成网格面片。关键在于将关节结构和部件网格均建模为量化三角形嵌入序列，形成统一的分层框架，支持自回归生成。部件结构首先以包围体和关节模式生成；第二个由结构引导的Transformer，再生成每个部件的三角面。为保证生成部件间的一致性，引入结构引导的条件机制，并融合局部网格连接性。MeshArt在性能上显著超越现有方法，结构覆盖率提升57.1%，网格生成FID下降209点。
原文摘要 · Abstract (English)
Articulated 3D object generation is fundamental for creating realistic, functional, and interactable virtual assets which are not simply static. We introduce MeshArt, a hierarchical transformer-based approach to generate articulated 3D meshes with clean, compact geometry, reminiscent of human-crafted 3D models. We approach articulated mesh generation in a part-by-part fashion across two stages. First, we generate a high-level articulation-aware object structure; then, based on this structural information, we synthesize each part's mesh faces. Key to our approach is modeling both articulation structures and part meshes as sequences of quantized triangle embeddings, leading to a unified hierarchical framework with transformers for autoregressive generation. Object part structures are first generated as their bounding primitives and articulation modes; a second transformer, guided by these articulation structures, then generates each part's mesh triangles. To ensure coherency among generated parts, we introduce structure-guided conditioning that also incorporates local part mesh connectivity. MeshArt shows significant improvements over state of the art, with 57.1% improvement in structure coverage and a 209-point improvement in mesh generation FID.
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。