Causal VAE

Concept

A 3D Variational Autoencoder designed for video generation where convolutions are asymmetric, ensuring that feature maps for a given frame only depend on itself and previous frames, allowing for streaming encoding and decoding.

Mentioned in 1 video

Videos Mentioning Causal VAE

Stanford CME296 Diffusion & Large Vision Models | Spring 2026 | Lecture 8 - Trending Topics

Stanford CME296 Diffusion & Large Vision Models | Spring 2026 | Lecture 8 - Trending Topics

Stanford Online

A 3D Variational Autoencoder designed for video generation where convolutions are asymmetric, ensuring that feature maps for a given frame only depend on itself and previous frames, allowing for streaming encoding and decoding.