# MeshOn: Intersection-Free Mesh-to-Mesh Composition

arXiv: https://arxiv.org/abs/2604.08799 · HTML: https://mlsanity.com/paper/2604.08799/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 27 of its 50 references that are in the map.
- First posted on arXiv 9 Apr 2026.

## Builds on (most cited first, 27 of 27)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [Magic3D: High-Resolution Text-to-3D Content Creation](https://mlsanity.com/paper/2211.10440/) (2022)
- [On the Continuity of Rotation Representations in Neural Networks](https://mlsanity.com/paper/1812.07035/) (2018)
- [Exploring CLIP for Assessing the Look and Feel of Images](https://mlsanity.com/paper/2207.12396/) (2022)
- [Open3D: A Modern Library for 3D Data Processing](https://mlsanity.com/paper/1801.09847/) (2018)
- [Evaluating Text-to-Visual Generation with Image-to-Text Generation](https://mlsanity.com/paper/2404.01291/) (2024)
- [InstantMesh: Efficient 3D Mesh Generation from a Single Image with Sparse-view Large Reconstruction Models](https://mlsanity.com/paper/2404.07191/) (2024)
- [Text2Mesh: Text-Driven Neural Stylization for Meshes](https://mlsanity.com/paper/2112.03221/) (2021)
- [Deep Closest Point: Learning Representations for Point Cloud Registration](https://mlsanity.com/paper/1905.03304/) (2019)
- [PointNetLK: Robust & Efficient Point Cloud Registration using PointNet](https://mlsanity.com/paper/1903.05711/) (2019)
- [Deep Global Registration](https://mlsanity.com/paper/2004.11540/) (2020)
- [Go-ICP: A Globally Optimal Solution to 3D ICP Point-Set Registration](https://mlsanity.com/paper/1605.03344/) (2016)
- [Deep Functional Maps: Structured Prediction for Dense Shape Correspondence](https://mlsanity.com/paper/1704.08686/) (2017)
- [REGTR: End-to-end Point Cloud Correspondences with Transformers](https://mlsanity.com/paper/2203.14517/) (2022)
- [TextDeformer: Geometry Manipulation using Text Guidance](https://mlsanity.com/paper/2304.13348/) (2023)
- [Meshtron: High-Fidelity, Artist-Like 3D Mesh Generation at Scale](https://mlsanity.com/paper/2412.09548/) (2024)
- [Instant3dit: Multiview Inpainting for Fast Editing of 3D Objects](https://mlsanity.com/paper/2412.00518/) (2024)
- [Dual Geometric Graph Network (DG2N) -- Iterative network for deformable shape alignment](https://mlsanity.com/paper/2011.14723/) (2020)
- [SE(3) Diffusion Model-based Point Cloud Registration for Robust 6D Object Pose Estimation](https://mlsanity.com/paper/2310.17359/) (2023)
- [3D Highlighter: Localizing Regions on 3D Shapes via Text Descriptions](https://mlsanity.com/paper/2212.11263/) (2022)
- [MeshUp: Multi-Target Mesh Deformation via Blended Score Distillation](https://mlsanity.com/paper/2408.14899/) (2024)
- [Geometry in Style: 3D Stylization via Surface Normal Deformation](https://mlsanity.com/paper/2503.23241/) (2025)
- [DreamMesh: Jointly Manipulating and Texturing Triangle Meshes for Text-to-3D Generation](https://mlsanity.com/paper/2409.07454/) (2024)
- [Text-guided Controllable Mesh Refinement for Interactive 3D Modeling](https://mlsanity.com/paper/2406.01592/) (2024)
- [CRAFT: Designing Creative and Functional 3D Objects](https://mlsanity.com/paper/2412.03889/) (2024)
- [Efficient GPU Cloth Simulation with Non-distance Barriers and Subspace Reuse](https://mlsanity.com/paper/2403.19272/) (2024)

## Abstract (arXiv)

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.