发表机构
Adobe Research（Adobe研究院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
MeshQuery是一种无需训练的智能体方法，利用视觉语言模型和特定领域语言规划UV接缝，在多个网格数据集上显著减少图块数量和接缝长度，并获艺术家偏好。
AI 中文摘要
我们提出了MeshQuery，一种无需训练的智能体方法，用于自动对生产级四边形网格进行UV展开。视觉语言模型（VLM）使用一组边选择工具，根据以自然语言表达的特定领域UV展开知识，并辅以反馈循环进行细化，来规划符合艺术家风格的接缝。我们设计了一种可查询的网格表示，以及一种特定领域语言（DSL），使智能体能够按需检索网格信息，将接缝计划表示为基于拓扑、几何和语义网格属性的边选择算子的紧凑程序，并根据UV质量反馈进行迭代细化。在Adobe Substance 3D和Toys4K网格上，MeshQuery产生的图块数量比最强基线少2.9倍/4.29倍，接缝长度短1.63倍/1.7倍，专业艺术家在80.9%的比较中更青睐其结果。最终，将高层意图规划与低层边选择及紧凑网格表示解耦，使MeshQuery能够在不同的后端VLM上运行，并扩展到比自回归接缝预测大一个数量级的网格。
英文摘要
We present MeshQuery, a training-free agentic approach to automatic UV unwrapping of production-grade quad meshes. A Vision-Language Model (VLM) plans artist-aligned seams using a set of edge-selection tools, conditioned on domain-specific UV-unwrapping knowledge expressed in natural language and refined with a feedback loop. We design a queryable mesh representation together with a domain-specific language (DSL) that enables the agent to retrieve mesh information on demand, express a seam plan as a compact program of edge-selection operators over topological, geometric, and semantic mesh attributes, and iteratively refine it from UV quality feedback. On Adobe Substance 3D and Toys4K meshes, MeshQuery produces 2.9x/4.29x fewer charts and 1.63x/1.7x shorter seams than the strongest baseline, and professional artists prefer its results in 80.9% of comparisons. Ultimately, decoupling high-level intent planning from low-level edge selection and compact mesh representation lets MeshQuery run on different backend VLMs and scale to meshes an order of magnitude larger than autoregressive seam prediction
