Conference paper Open Access

Playable Video Generation

Willi Menapace; Stephane Lathuiliere; Sergey Tulyakov; Aliaksandr Siarohin; Elisa Ricci

This paper introduces the unsupervised learning problem of playable video generation (PVG). In PVG, we aim at allowing a user to control the generated video by selecting a discrete action at every time step as when playing a video game. The difficulty of the task lies both in learning semantically consistent actions and in generating realistic videos conditioned on the user input. We propose a
novel framework for PVG that is trained in a self-supervised manner on a large dataset of unlabelled videos. We employ an encoder-decoder architecture where the predicted action labels act as bottleneck. The network is constrained to learn a rich action space using, as main driving loss, a reconstruction loss on the generated video. We demonstrate the effectiveness of the proposed approach on several datasets with wide environment variety. Further details, code and examples are available on our project page: willimenapace.github.io/playable-video-generation-website.

Files (1.8 MB)
Name Size
Menapace_Playable_Video_Generation_CVPR_2021_paper.pdf
md5:e1f956e68ee86a60dc640ec1f848228c
1.8 MB Download
14
10
views
downloads
All versions This version
Views 1414
Downloads 1010
Data volume 17.5 MB17.5 MB
Unique views 1212
Unique downloads 99

Share

Cite as