用局部拟合的补丁表示法，实现高效3D形变建模。
Patch-based Representation and Learning for Efficient Deformation Modeling
- 通过局部拟合射流函数构建表面补丁表示，支持监督学习。
- 仅更新少量射流系数即可高效变形，速度远超传统方法。
- 适用于形状重建与衣物悬垂，通用性强且推理快10倍。
本文提出一种基于补丁的表面表示方法PolyFit，通过在局部表面补丁上拟合射流函数获得。该表示可从解析函数和真实数据中高效地进行有监督学习，并具备良好泛化能力。一旦训练完成，即可通过更新一组紧凑的射流系数实现多种表面的高效变形，无需逐顶点优化，适用于计算机视觉与图形学中的多项下游任务。我们在两个应用中验证了该方法：1）基于模板的形状重建（SfT），采用测试时优化，在保持竞争性精度的同时显著快于离线物理求解器，并在稍高运行时间下优于近期物理引导神经模拟器；2）衣物悬垂建模，训练了一个自监督、与网格和衣物类型无关的模型，可跨分辨率与服装类型泛化，推理速度相较强基线提升达一个数量级。
原文摘要 · Abstract (English)
In this paper, we present a patch-based representation of surfaces, PolyFit, which is obtained by fitting jet functions locally on surface patches. Such a representation can be learned efficiently in a supervised fashion from both analytic functions and real data. Once learned, it can be generalized to various types of surfaces. Using PolyFit, the surfaces can be efficiently deformed by updating a compact set of jet coefficients rather than optimizing per-vertex degrees of freedom for many downstream tasks in computer vision and graphics. We demonstrate the capabilities of our proposed methodologies with two applications: 1) Shape-from-template (SfT): where the goal is to deform the input 3D template of an object as seen in image/video. Using PolyFit, we adopt test-time optimization that delivers competitive accuracy while being markedly faster than offline physics-based solvers, and outperforms recent physics-guided neural simulators in accuracy at modest additional runtime. 2) Garment draping. We train a self-supervised, mesh- and garment-agnostic model that generalizes across resolutions and garment types, delivering up to an order-of-magnitude faster inference than strong baselines.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。