Motion Guided 3D Pose Estimation from Videos

Abstract

We propose a new loss function, called motion loss, for the problem of monocular 3D Human pose estimation from 2D pose. In computing motion loss, a simple yet effective representation for keypoint motion, called pairwise motion encoding, is introduced. 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 additional supervision from the motion loss. We experiment training UGCN with the motion loss on two large scale benchmarks: Human3.6M and MPI-INF-3DHP. Our model surpasses other state-of-the-art models by a large margin. It also demonstrates strong capacity in producing smooth 3D sequences and recovering keypoint motion.

References in corpus (5)

• Semi-Supervised Classification with Graph Convolutional Networks
• VNect: Real-time 3D Human Pose Estimation with a Single RGB Camera
• Lifting from the Deep: Convolutional 3D Pose Estimation from a Single Image
• Diffusion-Convolutional Neural Networks
• Trajectory Space Factorization for Deep Video-Based 3D Human Pose Estimation

Cited by in corpus (1)

• A Graph Attention Spatio-temporal Convolutional Network for 3D Human Pose Estimation in Video