Motion Projection Consistency Based 3D Human Pose Estimation with Virtual Bones from Monocular Videos

06/28/2021
by   Guangming Wang, et al.
0

Real-time 3D human pose estimation is crucial for human-computer interaction. It is cheap and practical to estimate 3D human pose only from monocular video. However, recent bone splicing based 3D human pose estimation method brings about the problem of cumulative error. In this paper, the concept of virtual bones is proposed to solve such a challenge. The virtual bones are imaginary bones between non-adjacent joints. They do not exist in reality, but they bring new loop constraints for the estimation of 3D human joints. The proposed network in this paper predicts real bones and virtual bones, simultaneously. The final length of real bones is constrained and learned by the loop constructed by the predicted real bones and virtual bones. Besides, the motion constraints of joints in consecutive frames are considered. The consistency between the 2D projected position displacement predicted by the network and the captured real 2D displacement by the camera is proposed as a new projection consistency loss for the learning of 3D human pose. The experiments on the Human3.6M dataset demonstrate the good performance of the proposed method. Ablation studies demonstrate the effectiveness of the proposed inter-frame projection consistency constraints and intra-frame loop constraints.

READ FULL TEXT

page 1

page 7

page 9

research
06/04/2022

SPGNet: Spatial Projection Guided 3D Human Pose Estimation in Low Dimensional Space

We propose a method SPGNet for 3D human pose estimation that mixes multi...
research
12/13/2016

Deep Convolutional Poses for Human Interaction Recognition in Monocular Videos

Human interaction recognition is a challenging problem in computer visio...
research
11/22/2017

Cascaded 3D Full-body Pose Regression from Single Depth Image at 100 FPS

There are increasingly real-time live applications in virtual reality, w...
research
11/30/2021

Camera Distortion-aware 3D Human Pose Estimation in Video with Optimization-based Meta-Learning

Existing 3D human pose estimation algorithms trained on distortion-free ...
research
08/13/2022

A new way of video compression via forward-referencing using deep learning

To exploit high temporal correlations in video frames of the same scene,...
research
03/30/2022

Spatial-Temporal Parallel Transformer for Arm-Hand Dynamic Estimation

We propose an approach to estimate arm and hand dynamics from monocular ...
research
01/08/2019

A Spatial-temporal 3D Human Pose Reconstruction Framework

3D human pose reconstruction from single-view camera is a difficult and ...

Please sign up or login with your details

Forgot password? Click here to reset