MeshOn: Intersection-Free Mesh-to-Mesh Composition
For digital artists and 3D content creators, MeshOn provides a practical tool for realistic mesh composition without intersections, directly integrating into existing workflows.
MeshOn enables intersection-free composition of two 3D meshes by aligning them using vision-language models and optimizing with geometric and physics-inspired losses, outperforming generative and registration methods in robustness and accuracy.
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.