Love Handles：用于具有紧支撑和低内存占用的变形控制柄的抽取算法
Love Handles: Decimation for Deformation Handles with Compact Support and Low Memory Footprints
浏览论文内容
中文总结 AI 辅助
该研究提出一种基于抽取的变形控制柄算法，通过迭代代数简化优化控制柄变形，实现复杂几何的实时弹性动力学模拟，在含796,623个四面体的网格上可达到实时性能，且内存占用低。
中文摘要 AI 辅助
通过物理模拟估计固体变形是计算机动画、工程和机器人等领域的重要问题。此类模拟计算成本高昂，当通过增加离散化级别细化对象表示时，扩展性较差。降阶方法（ROM）通过减少自由度数量来节省计算量，例如使用控制顶点组的“控制柄（handles）”。我们提出了首个基于抽取（decimation）的算法，用于计算稀疏、具有紧支撑的变形控制柄集。我们方法的核心是利用迭代代数简化，优化控制柄变形以匹配任何输入变形，例如线性振动模式。该方法适用于任何体积输入网格，包括高亏格或多孔特征的网格，因为我们不改变几何结构。我们还设计了一种高效算法来计算和更新紧支撑及其关联权重。我们利用紧支撑开发了一种高效的降阶求积计算方案。优化后，我们的控制柄提供了内存高效的解决方案，同时支持复杂几何的实时弹性动力学模拟。我们在多达796,623个四面体的多种四面体网格上展示了实时性能。
英文摘要
Estimating the deformation of solids via physical simulation is an important problem spanning fields such as computer animation, engineering and robotics. Such simulations are computationally expensive and scale poorly when the representation of an object is refined by increasing the level of discretization. Reduced Order Methods (ROM) offer computational savings by decreasing the number of degrees of freedom, for example by using \emph{handles} that control groups of vertices. We present the first decimation-based algorithm for computing a sparse, compactly supported set of deformation handles. The crux of our method utilizes iterative algebraic simplification to optimize handle deformation to match any input deformation, such as linear vibration modes. This applies to any volumetric input mesh, including those with high genus or porous features, since we do not alter the geometry. We also devise an efficient algorithm to compute and update compact supports and their associated weights. We leverage compact support to develop an efficient, reduced-cubature computation scheme. Once optimized, our handles offer a memory-efficient solution while enabling real-time elastodynamics simulation of complex geometry. We show real-time performance on a variety of tetrahedral meshes with up to 796,623 tetrahedra.
