SeamGen: Artist-Aligned UV Seam Generation via Graph Flow Matching

2026-07-14

AI Summary

Existing automatic UV seam generation methods struggle to simultaneously satisfy artistic preferences and industrial requirements, such as seam invisibility, semantic alignment, and geometric structure preservation. This work proposes SeamGen—the first framework to apply flow-matching generative models to UV seam generation—leveraging a Mesh Transformer that integrates local graph attention with global vertex self-attention to natively model mesh topology. SeamGen directly learns the distribution of seam labels from professionally authored data without relying on handcrafted objective functions. Benefiting from the training-free refinement capability of flow models, SeamGen enables both controllable generation and localized optimization. Experiments demonstrate that its outputs significantly outperform existing distortion-minimization and semantic-proxy approaches in terms of perceptual quality and alignment with artist preferences.

Abstract

UV seam placement is a critical yet labor-intensive step in 3D content creation, requiring artists to balance chart shape, seam concealment, and alignment with semantic and geometric features. Existing automatic methods are primarily based on per-object optimization, relying on handcrafted objectives to avoid distortion or on proxies from pretrained models to inject semantic information. However, these strategies are not always well aligned with seams used in industrial production pipelines, often resulting in layouts that deviate from artist-preferred seam patterns and practical production requirements. To address these limitations, we propose SeamGen, a generative model for UV seam generation that aligns with artist preferences and production requirements. Instead of depending on manually designed objectives and constraints, SeamGen learns the distribution of per-edge seam labels from a large corpus of existing seam layouts using a flow-matching generative model. A key challenge is that typical Transformer architectures used in flow matching models are designed for sequential representations, such as point clouds, and cannot naturally account for mesh topology. To enable mesh-native learning, we design a Mesh Transformer backbone that interleaves local graph attention over mesh edges with global self-attention across vertices, capturing both fine-grained geometric cues and long-range topological coherence. To further improve inference-time controllability and quality, we exploit the training-free inpainting capability of flow models for both localized seam refinement and constraint-guided seam generation. Extensive experiments show that by learning priors from professional seam layout data, SeamGen produces UV layouts that better align with artist-authored preferences and achieve superior perceptual quality compared with distortion-based and semantic-proxy baselines.

Problem

• UV seam generation
• artist alignment
• 3D content creation
• mesh topology
• production pipeline

Innovation

• flow matching
• UV seam generation
• Mesh Transformer
• artist-aligned generation
• graph attention