Investigating pose representations and motion contexts modeling for 3D motion prediction

• Main Authors: Liu, Zhenguang, Wu, Shuang, Jin, Shuyuan, Liu, Qi, Ji, Shouling, Lu, Shijian, Cheng, Li
• Other Authors: School of Computer Science and Engineering
• Format: Article
• Language: English
• Published: 2022
• Subjects: Engineering::Computer science and engineering; Motion Prediction; Motion Context
• Online Access: https://hdl.handle.net/10356/162631
• Institution: Nanyang Technological University

Predicting human motion from historical pose sequence is crucial for a machine to succeed in intelligent interactions with humans. One aspect that has been obviated so far, is the fact that how we represent the skeletal pose has a critical impact on the prediction results. Yet there is no effort that investigates across different pose representation schemes. We conduct an indepth study on various pose representations with a focus on their effects on the motion prediction task. Moreover, recent approaches build upon off-the-shelf RNN units for motion prediction. These approaches process input pose sequence sequentially and inherently have difficulties in capturing long-term dependencies. In this paper, we propose a novel RNN architecture termed AHMR for motion prediction which simultaneously models local motion contexts and a global context. We further explore a geodesic loss and a forward kinematics loss, which have more geometric significance than the widely employed L2 loss. Interestingly, we applied our method to a range of articulate objects including human, fish, and mouse. Empirical results show that our approach outperforms the state-of-the-art methods in short-term prediction and achieves much enhanced long-term prediction proficiency, such as retaining natural human-like motions over 50 seconds predictions. Our codes are released.