Sep 18, 2021 · This paper proposes Manifold-preserved GANs (MaF-GANs), which generalize Wasserstein GANs into high-dimensional form.

To stabilize the training of MaF-GANs, an operation with precise and universal solution for any K-Lipschitz continuity, called Topological Consistency is ...

In this paper1, we improve Generative Adversarial Net- works by incorporating a manifold learning step into the discriminator.

May 17, 2023 · This paper investigates the challenge of learning image manifolds, specifically pose manifolds, of 3D objects using limited training data.

In this paper1, we improve Generative Adversarial Net- works by incorporating a manifold learning step into the discriminator.

Duration: 19:57
Posted: Nov 29, 2023

We introduce structure- preserving GANs as a data-efficient framework for learning distributions with additional struc- ture such as group symmetry, by ...

Aug 15, 2024 · This research aims to investigate the manifold properties of synthetically generated data and introduces a novel framework for producing privacy-preserving ...

Motivated by the ability of the GANs generator to capture the data manifold well, we propose to estimate the tangent space to the data manifold using GANs and ...

Bibliographic details on Manifold-preserved GANs.