Imitation Learning for Human Pose Prediction

TL;DR

This paper introduces a reinforcement learning approach for human pose prediction using imitation learning, outperforming existing models in accuracy and training efficiency.

Contribution

It presents a novel reinforcement learning formulation and an imitation learning algorithm combining behavioral cloning and adversarial methods for human pose prediction.

Findings

Outperforms state-of-the-art models in accuracy

Achieves faster training times

Excels in both short-term and long-term predictions

Abstract

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.