Neural Wasserstein gradient flows for maximum mean discrepancies with Riesz kernels

F Altekrüger, J Hertrich, G Steidl - arXiv preprint arXiv:2301.11624, 2023 - arxiv.org
Wasserstein gradient flows of maximum mean discrepancy (MMD) functionals with non-
smooth Riesz kernels show a rich structure as singular measures can become absolutely …

[PDF][PDF] Unpaired image super-resolution with optimal transport maps

M Gazdieva, L Rout, A Korotin, A Filippov… - arXiv preprint arXiv …, 2022 - researchgate.net
Real-world image super-resolution (SR) tasks often do not have paired datasets limiting the
application of supervised techniques. As a result, the tasks are usually approached by …

Unsupervised image translation with distributional semantics awareness

Z Peng, H Wang, Y Weng, Y Yang, T Shao - Computational Visual Media, 2023 - Springer
Unsupervised image translation (UIT) studies the mapping between two image domains.
Since such mappings are under-constrained, existing research has pursued various …