Robust Biharmonic Skinning Using Geometric Fields
Skinning is a popular way to rig and deform characters for animation, to compute reduced-
order simulations, and to define features for geometry processing. Methods built on skinning …
order simulations, and to define features for geometry processing. Methods built on skinning …
Scaling physics-informed hard constraints with mixture-of-experts
N Chalapathi, Y Du, A Krishnapriyan - arXiv preprint arXiv:2402.13412, 2024 - arxiv.org
Imposing known physical constraints, such as conservation laws, during neural network
training introduces an inductive bias that can improve accuracy, reliability, convergence, and …
training introduces an inductive bias that can improve accuracy, reliability, convergence, and …
Neural Monte Carlo Fluid Simulation
The idea of using a neural network to represent continuous vector fields (ie, neural fields)
has become popular for solving PDEs arising from physics simulations. Here, the classical …
has become popular for solving PDEs arising from physics simulations. Here, the classical …