让两个3D模型无穿插地自然组合，适合数字艺术创作。
MeshOn: Intersection-Free Mesh-to-Mesh Composition
- 用视觉语言模型初始化对齐，再通过几何与物理损失优化位置。
- 避免表面交叠，支持不同材质和目标区域的配件组合。
- 可直接融入艺术家工作流，比生成式方法更准确可靠。
我们提出MeshOn，一种在物理和语义上都真实合理的两输入网格组合方法。给定一个配件、一个带有用户指定目标区域的基础网格，以及可选的文本描述，MeshOn采用多步优化框架，将网格合理贴合且防止交叠。首先通过视觉-语言模型驱动的结构化对齐方案初始化刚性姿态，随后结合吸引性几何损失与类物理屏障损失进行优化，防止表面穿透。最后借助扩散先验完成最终形变。该方法成功实现多种材质配件在广泛目标区域上的自然组合，专为无缝集成现有数字艺术流程设计。通过与生成式方法及传统配准算法对比，验证了其鲁棒性与准确性。
原文摘要 · Abstract (English)
We propose MeshOn, a method that finds physically and semantically realistic compositions of two input meshes. Given an accessory, a base mesh with a user-defined target region, and optional text strings for both meshes, MeshOn uses a multi-step optimization framework to realistically fit the meshes onto each other while preventing intersections. We initialize the shapes' rigid configuration via a structured alignment scheme using Vision-to-Language Models, which we then optimize using a combination of attractive geometric losses, and a physics-inspired barrier loss that prevents surface intersections. We then obtain a final deformation of the object, assisted by a diffusion prior. Our method successfully fits accessories of various materials over a breadth of target regions, and is designed to fit directly into existing digital artist workflows. We demonstrate the robustness and accuracy of our pipeline by comparing it with generative approaches and traditional registration algorithms.
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。