paper-with-me

Papers

Paired Wasserstein Autoencoders for Conditional Sampling

2024-12-10 · Moritz Piening, Matthias Chung

Wasserstein distances greatly influenced and coined various types of generative neural network models. Wasserstein autoencoders are particularly notable for their mathematical simplicity and straight-forward implementation. However, their adaptation to the conditional case displays theoretical difficulties. As a remedy, we propose the use of two paired autoencoders. Under the assumption of an optimal autoencoder pair, we leverage the pairwise independence condition of our prescribed Gaussian latent distribution to overcome this theoretical hurdle. We conduct several experiments to showcase the practical applicability of the resulting paired Wasserstein autoencoders. Here, we consider imaging tasks and enable conditional sampling for denoising, inpainting, and unsupervised image translation. Moreover, we connect our image translation model to the Monge map behind Wasserstein-2 distances.

📄 PDF Abstract BibTeX arXiv:2412.07586

Code (0)

등록된 구현이 없습니다.

Tasks

DenoisingTranslation

Similar Papers 제목 키워드 기반

Conditional Sampling via Wasserstein Autoencoders and Triangular Transport

2026-04-03 · Mohammad Al-Jarrah, Michele Martino, Marcus Yim, Bamdad Hosseini 외 arxiv

We present Conditional Wasserstein Autoencoders (CWAEs), a framework for conditional simulation that exploits low-dimensional structure in both the conditioned and the conditioning variables. The key idea is to modify a …

Y-Diagonal Couplings: Approximating Posteriors with Conditional Wasserstein Distances

2023-10-20 · Jannis Chemseddine, Paul Hagemann, Christian Wald

In inverse problems, many conditional generative models approximate the posterior measure by minimizing a distance between the joint measure and its learned approximation. While this approach also controls the distance b…

Generative Class-conditional Autoencoders

2014-12-22 · Jan Rudy, Graham Taylor

Recent work by Bengio et al. (2013) proposes a sampling procedure for denoising autoencoders which involves learning the transition operator of a Markov chain. The transition operator is typically unimodal, which limits …

Denoising

Semi-Supervised Generative Learning via Latent Space Distribution Matching

2026-03-04 · Kwong Yu Chong, Long Feng arxiv

We introduce Latent Space Distribution Matching (LSDM), a novel framework for semi-supervised generative modeling of conditional distributions. LSDM operates in two stages: (i) learning a low-dimensional latent space fro…

Image Super-Resolution

Conditional Sampling of Variational Autoencoders via Iterated Approximate Ancestral Sampling

2023-08-17 · Vaidotas Simkus, Michael U. Gutmann

Conditional sampling of variational autoencoders (VAEs) is needed in various applications, such as missing data imputation, but is computationally intractable. A principled choice for asymptotically exact conditional sam…

Imputation