most citedSolution of physics-based inverse problems using conditional generative adversarial networks with full gradient penalty

3 citations · 4 across the 3 of their papers we have counts for

collaborators
Showing cs.CEShow all

1 paper · 1 filter

cs.CE2023

A dimension-reduced variational approach for solving physics-based inverse problems using generative adversarial network priors and normalizing flows

Agnimitra Dasgupta, Dhruv V Patel, Deep Ray +2

We propose a novel modular inference approach combining two different generative models -- generative adversarial networks (GAN) and normalizing flows -- to approximate the posteri…