Learning to Decompose and Disentangle Representations for Video Prediction

06/11/2018
by   Jun-Ting Hsieh, et al.
4

Our goal is to predict future video frames given a sequence of input frames. Despite large amounts of video data, this remains a challenging task because of the high-dimensionality of video frames. We address this challenge by proposing the Decompositional Disentangled Predictive Auto-Encoder (DDPAE), a framework that combines structured probabilistic models and deep networks to automatically (i) decompose the high-dimensional video that we aim to predict into components, and (ii) disentangle each component to have low-dimensional temporal dynamics that are easier to predict. Crucially, with an appropriately specified generative model of video frames, our DDPAE is able to learn both the latent decomposition and disentanglement without explicit supervision. For the Moving MNIST dataset, we show that DDPAE is able to recover the underlying components (individual digits) and disentanglement (appearance and location) as we would intuitively do. We further demonstrate that DDPAE can be applied to the Bouncing Balls dataset involving complex interactions between multiple objects to predict the video frame directly from the pixels and recover physical states without explicit supervision.

READ FULL TEXT

page 2

page 6

page 7

page 8

page 12

page 13

page 14

research
11/17/2020

Mutual Information Based Method for Unsupervised Disentanglement of Video Representation

Video Prediction is an interesting and challenging task of predicting fu...
research
02/25/2019

Generative Models for Low-Rank Video Representation and Reconstruction

Finding compact representation of videos is an essential component in al...
research
03/04/2019

VideoFlow: A Flow-Based Generative Model for Video

Generative models that can model and predict sequences of future events ...
research
05/24/2021

Taylor saves for later: disentanglement for video prediction using Taylor representation

Video prediction is a challenging task with wide application prospects i...
research
09/07/2021

Simple Video Generation using Neural ODEs

Despite having been studied to a great extent, the task of conditional g...
research
10/16/2017

A Disentangled Recognition and Nonlinear Dynamics Model for Unsupervised Learning

This paper takes a step towards temporal reasoning in a dynamically chan...
research
03/01/2019

Video Extrapolation with an Invertible Linear Embedding

We predict future video frames from complex dynamic scenes, using an inv...

Please sign up or login with your details

Forgot password? Click here to reset