Using Deep Learning for Depth Estimation and 3D Reconstruction of Humans
Publikation, 2020
Outline
A. Freller, G. Zwettler - Using Deep Learning for Depth Estimation and 3D Reconstruction of Humans - Proceedings of the 32th EUROPEAN MODELING AND SIMULATION SYMPOSIUM, Athen, Griechenland, 2020, pp. 6
Abstract
Deep learning depth estimation from monocular video feed is a common strategy to get rough 3D surface information when
an RGB-D camera is not present. Depth information is of importance in many domains such as object localization, tracking,
and scene reconstruction in robotics and industrial environments from multiple camera views. The convolutional neural
networks UpProjection, DORN, and Encoder/Decoder are evaluated on hybrid training datasets enriched by CGI data. The
highest accuracy results are derived from the UpProjection network with a relative deviation of 1.77% to 2.69% for CAD-120
and SMV dataset respectively. It is shown, that incorporation of front and side view allows to increase the achievable depth
estimation for human body images. With the incorporation of a second view for the SDV dataset, the error is reduced from
6.69% to 6.16%. For the target domain of this depth estimation, the 3D human body reconstruction from aligned images in
T-pose, plain silhouette reconstruction generally leads to acceptable results. Nevertheless, additionally incorporating the
rough depth approximation in the future, concave areas at the chest, breast, and buttocks, currently not handled by the
silhouette reconstruction, can result in more realistic 3D body models by utilizing the deep learning outcome in a hybrid
approach.
Cookies helfen uns bei der Bereitstellung unserer Dienste. Durch die Nutzung unserer Dienste erklären Sie sich damit einverstanden, dass wir Cookies setzen.