Motion Guided 3D Pose Estimation from Videos
European Conference on Computer Vision(2020)
Abstract
We propose a new loss function, called motion loss, for supervising models for monocular 3D Human pose estimation from videos. It works by comparing the motion pattern of the prediction against ground truth key point trajectories. In computing motion loss, we introduce pairwise motion encoding, a simple yet effective representation for keypoint motion. We design a new graph convolutional network architecture, U-shaped GCN (UGCN). It captures both short-term and long-term motion information to fully leverage the supervision from the motion loss (Codes and models at http://wangjingbo.top/papers/ECCV2020-Video-Pose/MotionLossPage.html). We experiment training UGCN with the motion loss on two large scale benchmarks: Human3.6M and MPI-INF-3DHP. Our models surpass other state-of-the-art models by a large margin. It also demonstrates strong capacity in producing smooth 3D sequences and recovering keypoint motion.
MoreTranslated text
Key words
3d,motion
AI Read Science
Must-Reading Tree
Example
![](https://originalfileserver.aminer.cn/sys/aminer/pubs/mrt_preview.jpeg)
Generate MRT to find the research sequence of this paper
Chat Paper
Summary is being generated by the instructions you defined