Meshtron：规模化生成高保真、艺术家级的3D网格
Meshtron: High-Fidelity, Artist-Like 3D Mesh Generation at Scale
AI总结：
针对现有3D网格生成面数少、坐标分辨率低的问题，提出由四大核心组件支撑的自回归模型Meshtron，可生成高分辨率高保真的复杂3D网格，性能优于现有方法，助力多领域3D资产生成。
摘要：
网格是3D表面的基础表示形式。然而，创建高质量网格是一项劳动密集型任务，需要投入大量时间并具备3D建模专业知识。一个精致的物体通常需要超过10⁴个面才能被精准建模，但近期生成艺术家级网格的尝试仅能实现1.6K个面，且顶点坐标存在严重离散化问题。因此，同时提升最大面数和顶点坐标分辨率，对于生成真实、复杂3D物体的高质量网格至关重要。\n我们提出了Meshtron，这是一种新型自回归网格生成模型，能够生成最多64K个面、坐标分辨率达1024级的网格——面数比当前最优方法高出一个数量级以上，坐标分辨率是其8倍。Meshtron的可扩展性由四大核心组件支撑：（1）沙漏型神经架构；（2）截断序列训练；（3）滑动窗口推理；（4）一种可约束网格序列顺序的鲁棒采样策略。这使得该模型相比现有工作训练内存降低超50%，吞吐量提升2.5倍，且一致性更优。\nMeshtron能以前所未有的分辨率和保真度生成细节丰富的复杂3D物体网格，效果与专业艺术家创作的网格高度相近，为动画、游戏和虚拟环境领域生成更逼真的精细3D资产开辟了道路。
英文摘要：
Meshes are fundamental representations of 3D surfaces. However, creating high-quality meshes is a labor-intensive task that requires significant time and expertise in 3D modeling. While a delicate object often requires over $10^4$ faces to be accurately modeled, recent attempts at generating artist-like meshes are limited to $1.6$K faces and heavy discretization of vertex coordinates. Hence, scaling both the maximum face count and vertex coordinate resolution is crucial to producing high-quality meshes of realistic, complex 3D objects. We present Meshtron, a novel autoregressive mesh generation model able to generate meshes with up to 64K faces at 1024-level coordinate resolution --over an order of magnitude higher face count and $8{\times}$ higher coordinate resolution than current state-of-the-art methods. Meshtron's scalability is driven by four key components: (1) an hourglass neural architecture, (2) truncated sequence training, (3) sliding window inference, (4) a robust sampling strategy that enforces the order of mesh sequences. This results in over $50{\%}$ less training memory, $2.5{\times}$ faster throughput, and better consistency than existing works. Meshtron generates meshes of detailed, complex 3D objects at unprecedented levels of resolution and fidelity, closely resembling those created by professional artists, and opening the door to more realistic generation of detailed 3D assets for animation, gaming, and virtual environments.
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。
