2 papers
cs.CV2021
ARAPReg: An As-Rigid-As Possible Regularization Loss for Learning Deformable Shape Generators
Qixing Huang, Xiangru Huang, Bo Sun +3
This paper introduces an unsupervised loss for training parametric deformation shape generators. The key idea is to enforce the preservation of local rigidity among the generated s…
cs.LG2020
Learning Order Parameters from Videos of Dynamical Phases for Skyrmions with Neural Networks
Weidi Wang, Zeyuan Wang, Yinghui Zhang +2
The ability to recognize dynamical phenomena (e.g., dynamical phases) and dynamical processes in physical events from videos, then to abstract physical concepts and reveal physical…