Browsing by Author "Yin, KangKang"
Now showing items 1-4 of 4
-
Laplace–Beltrami Operator on Point Clouds Based on Anisotropic Voronoi Diagram
Qin, Hongxing; Chen, Yi; Wang, Yunhai; Hong, Xiaoyang; Yin, Kangkang; Huang, Hui (© 2018 The Eurographics Association and John Wiley & Sons Ltd., 2018)The symmetrizable and converged Laplace–Beltrami operator () is an indispensable tool for spectral geometrical analysis of point clouds. The , introduced by Liu et al. [LPG12] is guaranteed to be symmetrizable, but its ... -
Learning and Exploring Motor Skills with Spacetime Bounds
Ma, Li-Ke; Yang, Zeshi; Tong, Xin; Guo, Baining; Yin, KangKang (The Eurographics Association and John Wiley & Sons Ltd., 2021)Equipping characters with diverse motor skills is the current bottleneck of physics-based character animation. We propose a Deep Reinforcement Learning (DRL) framework that enables physics-based characters to learn and ... -
Linear Time Stable PD Controllers for Physics-based Character Animation
Yin, Zhiqi; Yin, KangKang (The Eurographics Association and John Wiley & Sons Ltd., 2020)In physics-based character animation, Proportional-Derivative (PD) controllers are commonly used for tracking reference motions in motor control tasks. Stable PD (SPD) controllers significantly improve the numerical stability ... -
Towards Robust Direction Invariance in Character Animation
Ma, Li-Ke; Yang, Zeshi; Guo, Baining; Yin, KangKang (The Eurographics Association and John Wiley & Sons Ltd., 2019)In character animation, direction invariance is a desirable property. That is, a pose facing north and the same pose facing south are considered the same; a character that can walk to the north is expected to be able to ...