paper-with-me

Papers

Diffusion Variational Autoencoders

2019-01-25 · Luis A. Pérez Rey, Vlado Menkovski, Jacobus W. Portegies

A standard Variational Autoencoder, with a Euclidean latent space, is structurally incapable of capturing topological properties of certain datasets. To remove topological obstructions, we introduce Diffusion Variational Autoencoders with arbitrary manifolds as a latent space. A Diffusion Variational Autoencoder uses transition kernels of Brownian motion on the manifold. In particular, it uses properties of the Brownian motion to implement the reparametrization trick and fast approximations to the KL divergence. We show that the Diffusion Variational Autoencoder is capable of capturing topological properties of synthetic datasets. Additionally, we train MNIST on spheres, tori, projective spaces, SO(3), and a torus embedded in R3. Although a natural dataset like MNIST does not have latent variables with a clear-cut topological structure, training it on a manifold can still highlight topological and geometrical properties.

📄 PDF Abstract BibTeX arXiv:1901.08991

Code (2)

luis-armando-perez-rey/diffusion_vae 공식 구현 tf
luis-armando-perez-rey/diffusion_vae_github tf

Methods 이 논문이 사용한 방법론

Solana Customer Service Number +1-833-534-1729 설명 없음

Similar Papers 제목 키워드 기반

Latent Diffusion Models with Masked AutoEncoders

2025-07-14 · Junho Lee, Jeongwoo Shin, Hyungwook Choi, Joonseok Lee arxiv

In spite of the remarkable potential of Latent Diffusion Models (LDMs) in image generation, the desired properties and optimal design of the autoencoders have been underexplored. In this work, we analyze the role of auto…

Image Generation

Diffusion Priors In Variational Autoencoders

2021-06-29 · ICML Workshop INNF 2021 7 · Antoine Wehenkel, Gilles Louppe

Among likelihood-based approaches for deep generative modelling, variational autoencoders (VAEs) offer scalable amortized posterior inference and fast sampling. However, VAEs are also more and more outperformed by compet…

Denoising

Schödinger Bridge Type Diffusion Models as an Extension of Variational Autoencoders

2024-12-24 · Kentaro Kaba, Reo Shimizu, Masayuki Ohzeki, Yuki Sughiyama

Generative diffusion models use time-forward and backward stochastic differential equations to connect the data and prior distributions. While conventional diffusion models (e.g., score-based models) only learn the backw…

Latent Diffusion Model without Variational Autoencoder

2025-10-17 · Minglei Shi, Haolin Wang, Wenzhao Zheng, Ziyang Yuan 외 arxiv

Recent progress in diffusion-based visual generation has largely relied on latent diffusion models with variational autoencoders (VAEs). While effective for high-fidelity synthesis, this VAE+diffusion paradigm suffers fr…

A Frequentist Statistical Introduction to Variational Inference, Autoencoders, and Diffusion Models

2025-10-21 · Yen-Chi Chen arxiv

While Variational Inference (VI) is central to modern generative models like Variational Autoencoders (VAEs) and Denoising Diffusion Models (DDMs), its pedagogical treatment is split across disciplines. In statistics, VI…