This project demonstrates the use of a Variational AutoEncoder (VAE) to learn a latent space representation of simple synthetic data: black-and-white images of circles with varying radius, x, and y ...
Reducio-VAE was developed to enable high compression ratio on videos, supporting efficient video generation. Existing 3D VAEs are generally extended from 2D VAE, which is designed for image generation ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results
Feedback