Goal-Conditioned Video Prediction

Oleh Rybkin, Karl Pertsch, Frederik Ebert, Dinesh Jayaraman, Chelsea Finn, Sergey Levine

TL;DR: We propose a new class of visual generative models: goal-conditioned predictors. We show experimentally that conditioning on the goal allows to reduce uncertainty and produce predictions over much longer horizons.

Abstract: Many processes can be concisely represented as a sequence of events leading from a starting state to an end state. Given raw ingredients, and a finished cake, an experienced chef can surmise the recipe. Building upon this intuition, we propose a new class of visual generative models: goal-conditioned predictors (GCP). Prior work on video generation largely focuses on prediction models that only observe frames from the beginning of the video. GCP instead treats videos as start-goal transformations, making video generation easier by conditioning on the more informative context provided by the first and final frames. Not only do existing forward prediction approaches synthesize better and longer videos when modified to become goal-conditioned, but GCP models can also utilize structures that are not linear in time, to accomplish hierarchical prediction. To this end, we study both auto-regressive GCP models and novel tree-structured GCP models that generate frames recursively, splitting the video iteratively into finer and finer segments delineated by subgoals. In experiments across simulated and real datasets, our GCP methods generate high-quality sequences over long horizons. Tree-structured GCPs are also substantially easier to parallelize than auto-regressive GCPs, making training and inference very efficient, and allowing the model to train on sequences that are thousands of frames in length.Finally, we demonstrate the utility of GCP approaches for imitation learning in the setting without access to expert actions. Videos are on the supplementary website: https://sites.google.com/view/video-gcp

Keywords: predictive models, video prediction, latent variable models