3D pose estimation and future motion prediction from 2D images

作者：

Highlights：

• Estimating 3D human body poses and predicting future 3D motions are jointly investigated with a novel image-grounded multitask learning framework.

• Lie algebra pose representation implicitly encodes strong physical constraints for estimating poses and motions of articulated objects.

• Accurate and realistic motion prediction can be obtained from 2D images and no long rely on 3D motion capture data input.

摘要

•Estimating 3D human body poses and predicting future 3D motions are jointly investigated with a novel image-grounded multitask learning framework.•Lie algebra pose representation implicitly encodes strong physical constraints for estimating poses and motions of articulated objects.•Accurate and realistic motion prediction can be obtained from 2D images and no long rely on 3D motion capture data input.

论文关键词：Pose estimation,Motion prediction,Multitask learning

论文评审过程：Received 14 June 2020, Revised 12 October 2021, Accepted 16 November 2021, Available online 19 November 2021, Version of Record 28 February 2022.

论文官网地址：https://doi.org/10.1016/j.patcog.2021.108439