Playable Video Generation
Novel framework for Playable Video Generation 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.
Main Characteristic
- Playable Video Generation that is trained in a self-supervised manner on a large dataset of unlabelled videos.
Last updated
12.01.2023 - 11:44