arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2504.19210cs.CV
收藏

FlexPara:灵活的神经表面参数化

FlexPara: Flexible Neural Surface Parameterization

City University of Hong Kong(香港城市大学);TiMi L1 Studio of Tencent Games(腾讯游戏天美L1工作室);Texas A&M University(德克萨斯A&M大学)

Yuming Zhao, Qijian Zhang, Junhui Hou, Jiazhi Xia, Wenping Wang, Ying He

AI总结:

针对传统表面参数化受限于拓扑与配置固定的问题,本文提出无监督神经优化框架FlexPara,通过几何可解释子网络构建双向映射与自适应多图分配,实现灵活可控的全局/多图参数化,实验验证其通用性与优越性。

摘要:

表面参数化是几何处理的基础任务,为3D资产的视觉呈现和众多下游形状分析场景奠定基础。传统参数化方法需要高质量网格三角剖分,且受限于特定简单拓扑,除非提供额外表面切割与分解。实际中,最优配置(如参数化域类型、切割缝分布、映射图数量)会随表面结构和任务特性大幅变化,因此需要更灵活可控的处理流程。为此,本文提出FlexPara,一种无监督神经优化框架,通过建立3D表面点与自适应变形2D UV坐标间的逐点映射,实现全局和多图表面参数化。我们巧妙设计并结合一系列几何可解释子网络(具有切割、变形、展开、包裹等特定功能),构建无需手动指定切割缝的全局参数化双向循环映射框架;此外,还构建了具有自适应学习图分配的多图参数化框架。大量实验证明了我们神经表面参数化范式的通用性、优越性和启发潜力。代码将公开于https://github.com/AidenZhao/FlexPara

英文摘要:

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

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑