PartUV: Part-Based UV Unwrapping of 3D Meshes

AI summary

Overview

Research area: Computer vision and computer graphics, specifically 3D geometry processing — automatic UV unwrapping and surface parameterization of triangle meshes.

Technical level: Advanced. The paper assumes familiarity with mesh parameterization, chart segmentation, seam cutting, distortion metrics, and learning-based part decomposition.

Scope: PartUV is a part-based UV unwrapping pipeline that combines a learned semantic part decomposition (PartField) with two new geometric heuristics inside a top-down recursive search, producing significantly fewer, part-aligned charts at low distortion and high success rates across four diverse mesh datasets. (Published at SIGGRAPH Asia 2025 Conference Papers; arXiv:2511.16659v2 [cs.CV], 17 Feb 2026. DOI: 10.1145/3757377.3763843.)

What This Paper Is About

UV unwrapping flattens a 3D surface into 2D so that textures, normal maps, roughness maps and similar surface information can be stored and edited in 2D space. Complex surfaces must be cut into multiple pieces called charts, and existing tools tend to over-fragment them — especially on AI-generated meshes that are noisy, bumpy and geometrically poorly conditioned — creating hundreds or thousands of charts, long seams and texture artifacts. PartUV's goal is to generate far fewer charts that align with the semantic parts of an object (for example a limb, a TV screen, a face) while keeping each chart's distortion below a user-specified threshold.

Key Contributions

1

Authors’ abstract

UV unwrapping flattens 3D surfaces to 2D with minimal distortion, often requiring the complex surface to be decomposed into multiple charts. Although extensively studied, existing UV unwrapping methods frequently struggle with AI-generated meshes, which are typically noisy, bumpy, and poorly conditioned. These methods often produce highly fragmented charts and suboptimal boundaries, introducing artifacts and hindering downstream tasks. We introduce PartUV, a part-based UV unwrapping pipeline that generates significantly fewer, part-aligned charts while maintaining low distortion. Built on top of a recent learning-based part decomposition method PartField, PartUV combines high-level semantic part decomposition with novel geometric heuristics in a top-down recursive framework. It ensures each chart's distortion remains below a user-specified threshold while minimizing the total number of charts. The pipeline integrates and extends parameterization and packing algorithms, incorporates dedicated handling of non-manifold and degenerate meshes, and is extensively parallelized for efficiency. Evaluated across four diverse datasets, including man-made, CAD, AI-generated, and Common Shapes, PartUV outperforms existing tools and recent neural methods in chart count and seam length, achieves comparable distortion, exhibits high success rates on challenging meshes, and enables new applications like part-specific multi-tiles packing. Our project page is at https://www.zhaoningwang.com/PartUV.