Direct Prediction of 3D Body Poses from Motion Compensated Sequences

We propose an efficient approach to exploiting motion information from consecutive frames of a video sequence to recover the 3D pose of people. Previous approaches typically compute candidate poses in individual frames and then link them in a post-processing step to resolve ambiguities. By contrast,...

Full description

Saved in:
Bibliographic Details
Published in2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) pp. 991 - 1000
Main Authors Tekin, Bugra, Rozantsev, Artem, Lepetit, Vincent, Fua, Pascal
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.06.2016
Subjects
Feature extraction
Motion compensation
Pose estimation
Spatiotemporal phenomena
Three-dimensional displays
Training
Two dimensional displays
Online AccessGet full text
ISSN1063-6919
DOI10.1109/CVPR.2016.113

Cover

More Information
Summary:We propose an efficient approach to exploiting motion information from consecutive frames of a video sequence to recover the 3D pose of people. Previous approaches typically compute candidate poses in individual frames and then link them in a post-processing step to resolve ambiguities. By contrast, we directly regress from a spatio-temporal volume of bounding boxes to a 3D pose in the central frame. We further show that, for this approach to achieve its full potential, it is essential to compensate for the motion in consecutive frames so that the subject remains centered. This then allows us to effectively overcome ambiguities and improve upon the state-of-the-art by a large margin on the Human3.6m, HumanEva, and KTH Multiview Football 3D human pose estimation benchmarks.
ISSN:1063-6919
DOI:10.1109/CVPR.2016.113