PartUV: Part-Based UV Unwrapping of 3D Meshes
Zhaoning Wang, Xinyue Wei, Ruoxi Shi, Xiaoshuai Zhang, Hao Su, Minghua Liu
2025-11-21
Summary
This paper introduces a new method called PartUV for taking 3D models and flattening them out into 2D images, which is a necessary step for things like applying textures or preparing models for games.
What's the problem?
Currently, existing methods for flattening 3D models struggle with models created by Artificial Intelligence. These AI-generated models are often messy and uneven, causing the flattening process to create a lot of separate pieces and jagged edges, which makes them harder to work with and can cause visual problems when the texture is applied.
What's the solution?
PartUV solves this by first breaking the 3D model down into meaningful parts, almost like identifying the different components of an object. Then, it flattens each part separately, making sure the stretching and distortion on each piece stays within acceptable limits. It uses a combination of smart algorithms and a recent AI technique to do this efficiently and with fewer separate pieces than other methods.
Why it matters?
This is important because it makes it easier to work with 3D models created by AI, which are becoming more common. By reducing the number of pieces and improving the quality of the flattened image, PartUV allows for better textures, more efficient use of resources, and opens up possibilities for new applications like arranging textures in a more organized way based on the model's parts.
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.