MeshArt：使用结构引导 Transformer 生成铰接网格
MeshArt: Generating Articulated Meshes with Structure-Guided Transformers
AI总结：
本文提出 MeshArt，通过分层 Transformer 先生成铰接结构、再生成各部件网格，并以结构引导条件保证一致性，显著提升铰接 3D 网格生成质量。
摘要：
铰接式 3D 物体生成对于创建逼真、实用且可交互、并非单纯静态的虚拟资产至关重要。我们提出 MeshArt，这是一种基于分层 Transformer 的方法，用于生成具有干净、紧凑几何形状的铰接式 3D 网格，令人联想到人工制作的 3D 模型。我们通过两个阶段以逐部件方式处理铰接网格生成。首先，生成高级的、感知铰接的物体结构；随后，基于该结构信息合成每个部件的网格面。我们方法的关键在于将铰接结构和部件网格都建模为量化三角形嵌入序列，从而形成一个统一的分层框架，并使用 Transformer 进行自回归生成。物体部件结构首先以其包围基元和铰接模式的形式生成；第二个 Transformer 在这些铰接结构的引导下，随后生成每个部件的网格三角形。为确保生成部件之间的一致性，我们引入了结构引导条件机制，该机制还融合了局部部件网格连通性。MeshArt 相较最先进方法表现出显著提升，结构覆盖率提高 57.1%，网格生成 FID 改善 209 点。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
