A potential flow generator that penalizes the Hamilton-Jacobi equation enforces L2 optimal transport regularity in GANs and flow models, demonstrated on 2D benchmarks and unpaired image translation.
Generative modeling using the sliced Wasserstein distance
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2019 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Potential Flow Generator with $L_2$ Optimal Transport Regularity for Generative Models
A potential flow generator that penalizes the Hamilton-Jacobi equation enforces L2 optimal transport regularity in GANs and flow models, demonstrated on 2D benchmarks and unpaired image translation.