Aggregated Multi-GANs for Controlled 3D Human Motion Prediction

Authors

  • Zhenguang Liu Zhejiang Gongshang University
  • Kedi Lyu Jilin University
  • Shuang Wu Nanyang Technological University
  • Haipeng Chen Jilin University
  • Yanbin Hao University of Science and Technology of China
  • Shouling Ji Zhejiang University

Keywords:

Motion & Tracking, (Deep) Neural Network Algorithms, Video Understanding & Activity Analysis, Dimensionality Reduction/Feature Selection

Abstract

Human motion prediction from historical pose sequence is at the core of many applications in machine intelligence. However, in current state-of-the-art methods, the predicted future motion is confined within the same activity. One can neither generate predictions that differ from the current activity, nor manipulate the body parts to explore various future possibilities. Undoubtedly, this greatly limits the usefulness and applicability of motion prediction. In this paper, we propose a generalization of the human motion prediction task in which control parameters can be readily incorporated to adjust the forecasted motion. Our method is compelling in that it enables manipulable motion prediction across activity types and allows customization of the human movement in a variety of fine-grained ways. To this aim, a simple yet effective composite GAN structure, consisting of local GANs for different body parts and aggregated via a global GAN is presented. The local GANs game in lower dimensions, while the global GAN adjusts in high dimensional space to avoid mode collapse. Extensive experiments show that our method outperforms state-of-the-art. The codes are available at https://github.com/herolvkd/AM-GAN.

Downloads

Published

2021-05-18

How to Cite

Liu, Z., Lyu, K., Wu, S., Chen, H., Hao, Y., & Ji, S. (2021). Aggregated Multi-GANs for Controlled 3D Human Motion Prediction. Proceedings of the AAAI Conference on Artificial Intelligence, 35(3), 2225-2232. Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/16321

Issue

Section

AAAI Technical Track on Computer Vision II