# SeamFlow: Structure-Aware Flow Matching on Edge Probabilities for Artist-Like UV Unwrapping

arXiv: https://arxiv.org/abs/2609.04751 · HTML: https://mlsanity.com/paper/2609.04751/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in 3D, point cloud and scene generation, one of 14 directions in Diffusion models.
- Builds on 26 of its 64 references that are in the map.
- First posted on arXiv 4 Sep 2026.

## Placed in

- Diffusion models / [3D, point cloud and scene generation](https://mlsanity.com/diffusion/3d-point-cloud-and-scene-generation/)

## Builds on (most cited first, 26 of 26)

- [Objaverse: A Universe of Annotated 3D Objects](https://mlsanity.com/paper/2212.08051/) (2022)
- [Objaverse-XL: A Universe of 10M+ 3D Objects](https://mlsanity.com/paper/2307.05663/) (2023)
- [AtlasNet: A Papier-Mach'e Approach to Learning 3D Surface Generation](https://mlsanity.com/paper/1802.05384/) (2018)
- [PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategies](https://mlsanity.com/paper/2206.04670/) (2022)
- [PointGroup: Dual-Set Point Grouping for 3D Instance Segmentation](https://mlsanity.com/paper/2004.01658/) (2020)
- [Michelangelo: Conditional 3D Shape Generation based on Shape-Image-Text Aligned Latent Representation](https://mlsanity.com/paper/2306.17115/) (2023)
- [Learning elementary structures for 3D shape generation and matching](https://mlsanity.com/paper/1908.04725/) (2019)
- [NeuTex: Neural Texture Mapping for Volumetric Neural Rendering](https://mlsanity.com/paper/2103.00762/) (2021)
- [PARTFIELD: Learning 3D Feature Fields for Part Segmentation and Beyond](https://mlsanity.com/paper/2504.11451/) (2025)
- [Shape Reconstruction by Learning Differentiable Surface Representations](https://mlsanity.com/paper/1911.11227/) (2019)
- [SAM-guided Graph Cut for 3D Instance Segmentation](https://mlsanity.com/paper/2312.08372/) (2023)
- [Neural Surface Maps](https://mlsanity.com/paper/2103.16942/) (2021)
- [Nuvo: Neural UV Mapping for Unruly 3D Representations](https://mlsanity.com/paper/2312.05283/) (2023)
- [TearingNet: Point Cloud Autoencoder to Learn Topology-Friendly Representations](https://mlsanity.com/paper/2006.10187/) (2020)
- [Deep Unsupervised Learning of 3D Point Clouds via Graph Topology Inference and Filtering](https://mlsanity.com/paper/1905.04571/) (2019)
- [Flatten Anything: Unsupervised Neural Surface Parameterization](https://mlsanity.com/paper/2405.14633/) (2024)
- [TEMPO: Feature-Endowed Teichm"uller Extremal Mappings of Point Clouds](https://mlsanity.com/paper/1511.06624/) (2015)
- [Spherical Conformal Parameterization of Genus-0 Point Clouds for Meshing](https://mlsanity.com/paper/1508.07569/) (2015)
- [DA Wand: Distortion-Aware Selection using Neural Mesh Parameterization](https://mlsanity.com/paper/2212.06344/) (2022)
- [PartUV: Part-Based UV Unwrapping of 3D Meshes](https://mlsanity.com/paper/2511.16659/) (2025)
- [Free-boundary conformal parameterization of point clouds](https://mlsanity.com/paper/2010.15399/) (2020)
- [MeshTailor: Cutting Seams via Generative Mesh Traversal](https://mlsanity.com/paper/2603.27309/) (2026)
- [A Novel Stretch Energy Minimization Algorithm for Equiareal Parameterizations](https://mlsanity.com/paper/1708.07391/) (2017)
- [SeamCrafter: Enhancing Mesh Seam Generation for Artist UV Unwrapping via Reinforcement Learning](https://mlsanity.com/paper/2509.20725/) (2025)
- [Unsupervised Representation Learning for 3D Mesh Parameterization with Semantic and Visibility Objectives](https://mlsanity.com/paper/2509.25094/) (2025)
- [From Extrinsic to Intrinsic: Geodesic-Guided Representation Learning for 3D Geometric Data](https://mlsanity.com/paper/2606.02268/) (2026)

## Abstract (arXiv)

3D surface cutting and UV unwrapping are fundamental problems in computer graphics. Traditional geometric optimization methods mainly focus on reducing parameterization distortion, but they often overlook visual semantic coherence in seam layouts. Recent autoregressive generative methods improve semantic coherence, yet limited perception of mesh topology often causes inaccurate local cuts. To address these limitations, we introduce SeamFlow, a novel generative framework for 3D surface cutting. We reformulate the discrete mesh-cutting problem as continuous flow matching in a high-dimensional edge-probability space. Through continuous relaxation, SeamFlow learns a deterministic mapping from a Gaussian prior to a target seam-probability distribution. An evolution network couples local topological tokens with global shape priors and guides smooth probability flow through Ordinary Differential Equation solving. Compared with existing autoregressive generative frameworks, SeamFlow improves topology awareness through edge tokenization while eliminating both 3D spatial projection errors and artificial sequential-order bias. Extensive experiments demonstrate that SeamFlow achieves exceptional semantic coherence and remarkably low parameterization distortion. The project page is https://meshy-dev.github.io/seamflow.