TY - GEN
T1 - Volumetric representation of human body parts using superquadrics
AU - Hachiuma, Ryo
AU - Saito, Hideo
N1 - Funding Information:
In the future, we will develop applications that leverage the two big advantages of SQs. First, as SQ scale parameters directly represent the size of each body part, the size of a human body can be easily measured from a single view and used to virtually fit or customize clothes. Second, as the shape of the hidden area is recovered using SQs, the recovered information can be used to generate free viewpoint images. ACKNOWLEDGMENTS This work was supported by AIP-PRISM, Japan Science and Technology Agency, Grant Number JPMJCR18Y2, Japan.
Publisher Copyright:
© 2019 IEEE.
PY - 2019/10
Y1 - 2019/10
N2 - Superquadrics are one of the ideal shape representations for adapting various kinds of primitive shapes with a single equation. This paper revisits the task of representing a 3D human body with multiple superquadrics. As a single superquadric surface can only represent symmetric primitive shapes, we present a method that segments the human body into body parts to estimate their superquadric parameters. Moreover, we propose a novel initial parameter estimation method by using 3D skeleton joints. The results show that superquadric parameters are estimated, which represent human body parts volumetrically.
AB - Superquadrics are one of the ideal shape representations for adapting various kinds of primitive shapes with a single equation. This paper revisits the task of representing a 3D human body with multiple superquadrics. As a single superquadric surface can only represent symmetric primitive shapes, we present a method that segments the human body into body parts to estimate their superquadric parameters. Moreover, we propose a novel initial parameter estimation method by using 3D skeleton joints. The results show that superquadric parameters are estimated, which represent human body parts volumetrically.
KW - Semantic segmentation
KW - Superquadrics
UR - http://www.scopus.com/inward/record.url?scp=85078751389&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85078751389&partnerID=8YFLogxK
U2 - 10.1109/ISMAR-Adjunct.2019.00-50
DO - 10.1109/ISMAR-Adjunct.2019.00-50
M3 - Conference contribution
AN - SCOPUS:85078751389
T3 - Adjunct Proceedings of the 2019 IEEE International Symposium on Mixed and Augmented Reality, ISMAR-Adjunct 2019
SP - 187
EP - 188
BT - Adjunct Proceedings of the 2019 IEEE International Symposium on Mixed and Augmented Reality, ISMAR-Adjunct 2019
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 18th IEEE International Symposium on Mixed and Augmented Reality, ISMAR-Adjunct 2019
Y2 - 14 October 2019 through 18 October 2019
ER -