# SeamCrafter: Enhancing Mesh Seam Generation for Artist UV Unwrapping via Reinforcement Learning

arXiv: https://arxiv.org/abs/2509.20725 · HTML: https://mlsanity.com/paper/2509.20725/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 30 references that are in the map.
- First posted on arXiv 25 Sep 2025.

## Builds on (most cited first, 16 of 16)

- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [ShapeNet: An Information-Rich 3D Model Repository](https://mlsanity.com/paper/1512.03012/) (2015)
- [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)
- [3DShape2VecSet: A 3D Shape Representation for Neural Fields and Generative Diffusion Models](https://mlsanity.com/paper/2301.11445/) (2023)
- [3D-FUTURE: 3D Furniture shape with TextURE](https://mlsanity.com/paper/2009.09633/) (2020)
- [Using Shape to Categorize: Low-Shot Learning with an Explicit Shape Bias](https://mlsanity.com/paper/2101.07296/) (2021)
- [Hierarchical Transformers Are More Efficient Language Models](https://mlsanity.com/paper/2110.13711/) (2021)
- [Meshtron: High-Fidelity, Artist-Like 3D Mesh Generation at Scale](https://mlsanity.com/paper/2412.09548/) (2024)
- [Scaling Mesh Generation via Compressive Tokenization](https://mlsanity.com/paper/2411.07025/) (2024)
- [DeepMesh: Auto-Regressive Artist-mesh Creation with Reinforcement Learning](https://mlsanity.com/paper/2503.15265/) (2025)
- [Nuvo: Neural UV Mapping for Unruly 3D Representations](https://mlsanity.com/paper/2312.05283/) (2023)
- [Flatten Anything: Unsupervised Neural Surface Parameterization](https://mlsanity.com/paper/2405.14633/) (2024)
- [Generating 3D House Wireframes with Semantics](https://mlsanity.com/paper/2407.12267/) (2024)
- [Auto-Regressive Surface Cutting](https://mlsanity.com/paper/2506.18017/) (2025)

## Built on by (most cited first, 2 of 2)

- [AssetGen: Deployable 3D Asset Generation at Interactive Speed](https://mlsanity.com/paper/2605.26137/) (2026)
- [SeamFlow: Structure-Aware Flow Matching on Edge Probabilities for Artist-Like UV Unwrapping](https://mlsanity.com/paper/2609.04751/) (2026)

## Abstract (arXiv)

Mesh seams play a pivotal role in partitioning 3D surfaces for UV parametrization and texture mapping. Poorly placed seams often result in severe UV distortion or excessive fragmentation, thereby hindering texture synthesis and disrupting artist workflows. Existing methods frequently trade one failure mode for another-producing either high distortion or many scattered islands. To address this, we introduce SeamCrafter, an autoregressive GPT-style seam generator conditioned on point cloud inputs. SeamCrafter employs a dual-branch point-cloud encoder that disentangles and captures complementary topological and geometric cues during pretraining. To further enhance seam quality, we fine-tune the model using Direct Preference Optimization (DPO) on a preference dataset derived from a novel seam-evaluation framework. This framework assesses seams primarily by UV distortion and fragmentation, and provides pairwise preference labels to guide optimization. Extensive experiments demonstrate that SeamCrafter produces seams with substantially lower distortion and fragmentation than prior approaches, while preserving topological consistency and visual fidelity.