Compositional Video Synthesis with Action Graphs
This addresses the problem of compositional video synthesis for applications in video generation and editing, representing an incremental advance by introducing a graph-based method to handle timed actions.
The paper tackles the challenge of generating videos conditioned on multiple coordinated and simultaneous timed actions by proposing an Action Graph representation and the AG2Vid model, which shows improved visual quality and semantic consistency on datasets like CATER and Something-Something V2, with zero-shot abilities for novel action compositions.
Videos of actions are complex signals containing rich compositional structure in space and time. Current video generation methods lack the ability to condition the generation on multiple coordinated and potentially simultaneous timed actions. To address this challenge, we propose to represent the actions in a graph structure called Action Graph and present the new ``Action Graph To Video'' synthesis task. Our generative model for this task (AG2Vid) disentangles motion and appearance features, and by incorporating a scheduling mechanism for actions facilitates a timely and coordinated video generation. We train and evaluate AG2Vid on the CATER and Something-Something V2 datasets, and show that the resulting videos have better visual quality and semantic consistency compared to baselines. Finally, our model demonstrates zero-shot abilities by synthesizing novel compositions of the learned actions. For code and pretrained models, see the project page https://roeiherz.github.io/AG2Video