Imitation Learning for Human Pose Prediction
This addresses the challenging problem of human motion dynamics prediction in computer vision, with incremental improvements over existing methods.
The paper tackles human pose prediction by proposing a reinforcement learning formulation with an imitation learning algorithm combining behavioral cloning and generative adversarial imitation learning. The method outperforms all existing state-of-the-art baselines by large margins in both short-term and long-term predictions and achieves huge training speed advantages.
Modeling and prediction of human motion dynamics has long been a challenging problem in computer vision, and most existing methods rely on the end-to-end supervised training of various architectures of recurrent neural networks. Inspired by the recent success of deep reinforcement learning methods, in this paper we propose a new reinforcement learning formulation for the problem of human pose prediction, and develop an imitation learning algorithm for predicting future poses under this formulation through a combination of behavioral cloning and generative adversarial imitation learning. Our experiments show that our proposed method outperforms all existing state-of-the-art baseline models by large margins on the task of human pose prediction in both short-term predictions and long-term predictions, while also enjoying huge advantage in training speed.