Disentangled Dynamic Representations from Unordered Data

by   Leonhard Helminger, et al.
ETH Zurich
Disney Research

We present a deep generative model that learns disentangled static and dynamic representations of data from unordered input. Our approach exploits regularities in sequential data that exist regardless of the order in which the data is viewed. The result of our factorized graphical model is a well-organized and coherent latent space for data dynamics. We demonstrate our method on several synthetic dynamic datasets and real video data featuring various facial expressions and head poses.


page 3

page 4


A Deep Generative Model for Disentangled Representations of Sequential Data

We present a VAE architecture for encoding and generating high dimension...

Learning Disentangled Representations of Video with Missing Data

Missing data poses significant challenges while learning representations...

Face Identity Disentanglement via Latent Space Mapping

Learning disentangled representations of data is a fundamental problem i...

Disentangling Representations using Gaussian Processes in Variational Autoencoders for Video Prediction

We introduce MGP-VAE, a variational autoencoder which uses Gaussian proc...

Latent Traversals in Generative Models as Potential Flows

Despite the significant recent progress in deep generative models, the u...

A Deep Generative Model for Interactive Data Annotation through Direct Manipulation in Latent Space

The impact of machine learning (ML) in many fields of application is con...

A Deep Generative Model for Matrix Reordering

Depending on the node ordering, an adjacency matrix can highlight distin...

Please sign up or login with your details

Forgot password? Click here to reset