FlexPara: Flexible Neural Surface Parameterization

2025-04-27

AI Summary

Traditional surface parameterization relies on high-quality meshes and manually designed cuts, struggling with complex topologies and non-manifold structures; moreover, configurations—such as domain type, cut distribution, and chart count—lack generality. This paper proposes an unsupervised neural optimization framework for global single-chart and adaptive multi-chart parameterization without pre-specified cuts. It employs a learnable bidirectional cyclic mapping—“cutting–deformation–unfolding–wrapping”—to directly map 3D points to deformable 2D UV coordinates. Key components include a geometrically interpretable subnet, unsupervised cycle-consistency constraints, and an adaptive chart assignment mechanism. The method is topology-agnostic, natively supports multi-chart partitioning, significantly reduces distortion, and improves fidelity—especially on complex and non-manifold surfaces. It enables end-to-end training and generalization across unseen geometries. Code is publicly available.

Technology Category

• Machine Learning: Learning with Manifolds
• Computer Vision: Learning & Optimization for CV
• Natural Language Processing: Learning & Optimization for NLP

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Economics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystems

Abstract

Surface parameterization is a fundamental geometry processing task, laying the foundations for the visual presentation of 3D assets and numerous downstream shape analysis scenarios. Conventional parameterization approaches demand high-quality mesh triangulation and are restricted to certain simple topologies unless additional surface cutting and decomposition are provided. In practice, the optimal configurations (e.g., type of parameterization domains, distribution of cutting seams, number of mapping charts) may vary drastically with different surface structures and task characteristics, thus requiring more flexible and controllable processing pipelines. To this end, this paper introduces FlexPara, an unsupervised neural optimization framework to achieve both global and multi-chart surface parameterizations by establishing point-wise mappings between 3D surface points and adaptively-deformed 2D UV coordinates. We ingeniously design and combine a series of geometrically-interpretable sub-networks, with specific functionalities of cutting, deforming, unwrapping, and wrapping, to construct a bi-directional cycle mapping framework for global parameterization without the need for manually specified cutting seams. Furthermore, we construct a multi-chart parameterization framework with adaptively-learned chart assignment. Extensive experiments demonstrate the universality, superiority, and inspiring potential of our neural surface parameterization paradigm. The code will be publicly available at https://github.com/AidenZhao/FlexPara

Problem

• Achieving flexible neural surface parameterization without manual cutting seams
• Adapting parameterization to varying surface structures and task needs
• Enabling both global and multi-chart mappings via neural optimization

Innovation

• Unsupervised neural optimization for surface parameterization
• Bi-directional cycle mapping without manual cutting
• Adaptively-learned multi-chart parameterization framework