G3AN: Disentangling Appearance and Motion for Video Generation
This work addresses the problem of video generation for applications in facial expressions and human actions, offering a novel approach but is incremental in building on existing generative models.
The paper tackles the challenge of generating realistic human videos by disentangling appearance and motion, introducing G3AN, a spatio-temporal generative model that significantly outperforms state-of-the-art methods on datasets like MUG, UvA-NEMO, Weizmann, and UCF101.
Creating realistic human videos entails the challenge of being able to simultaneously generate both appearance, as well as motion. To tackle this challenge, we introduce G$^{3}$AN, a novel spatio-temporal generative model, which seeks to capture the distribution of high dimensional video data and to model appearance and motion in disentangled manner. The latter is achieved by decomposing appearance and motion in a three-stream Generator, where the main stream aims to model spatio-temporal consistency, whereas the two auxiliary streams augment the main stream with multi-scale appearance and motion features, respectively. An extensive quantitative and qualitative analysis shows that our model systematically and significantly outperforms state-of-the-art methods on the facial expression datasets MUG and UvA-NEMO, as well as the Weizmann and UCF101 datasets on human action. Additional analysis on the learned latent representations confirms the successful decomposition of appearance and motion. Source code and pre-trained models are publicly available.