Generating Smooth Pose Sequences for Diverse Human Motion Prediction
This work addresses the need for efficient and realistic diverse and controllable human motion prediction in computer vision and robotics, though it is incremental as it builds on existing stochastic methods.
The paper tackles the problem of predicting multiple possible future human motions from a single past pose sequence by introducing a unified deep generative network that outperforms state-of-the-art baselines in sample diversity and accuracy on benchmark datasets Human3.6M and HumanEva-I.
Recent progress in stochastic motion prediction, i.e., predicting multiple possible future human motions given a single past pose sequence, has led to producing truly diverse future motions and even providing control over the motion of some body parts. However, to achieve this, the state-of-the-art method requires learning several mappings for diversity and a dedicated model for controllable motion prediction. In this paper, we introduce a unified deep generative network for both diverse and controllable motion prediction. To this end, we leverage the intuition that realistic human motions consist of smooth sequences of valid poses, and that, given limited data, learning a pose prior is much more tractable than a motion one. We therefore design a generator that predicts the motion of different body parts sequentially, and introduce a normalizing flow based pose prior, together with a joint angle loss, to achieve motion realism.Our experiments on two standard benchmark datasets, Human3.6M and HumanEva-I, demonstrate that our approach outperforms the state-of-the-art baselines in terms of both sample diversity and accuracy. The code is available at https://github.com/wei-mao-2019/gsps