TY - GEN
T1 - SILHOUETTE-BASED SYNTHETIC DATA GENERATION FOR 3D HUMAN POSE ESTIMATION WITH A SINGLE WRIST-MOUNTED 360° CAMERA
AU - Hori, Ryosuke
AU - Hachiuma, Ryo
AU - Saito, Hideo
AU - Isogawa, Mariko
AU - Mikami, Dan
N1 - Publisher Copyright:
© 2021 IEEE
PY - 2021
Y1 - 2021
N2 - In this paper, we propose a framework for 3D human pose estimation with a single 360◦ camera mounted on the user’s wrist. Perceiving a 3D human pose with such a simple setting has remarkable potential for various applications (e.g., daily-living activity monitoring, motion analysis for sports enhancement). However, no existing work has tackled this task due to the difficulty of estimating a human pose from a single camera image in which only a part of the human body is captured and the lack of training data. Therefore, we propose an effective method for translating wrist-mounted 360◦ camera images into 3D human poses. We also propose silhouette-based synthetic data generation dedicated to this task, which enables us to bridge the domain gap between real-world data and synthetic data. We achieved higher estimation accuracy quantitatively and qualitatively compared with other baseline methods.
AB - In this paper, we propose a framework for 3D human pose estimation with a single 360◦ camera mounted on the user’s wrist. Perceiving a 3D human pose with such a simple setting has remarkable potential for various applications (e.g., daily-living activity monitoring, motion analysis for sports enhancement). However, no existing work has tackled this task due to the difficulty of estimating a human pose from a single camera image in which only a part of the human body is captured and the lack of training data. Therefore, we propose an effective method for translating wrist-mounted 360◦ camera images into 3D human poses. We also propose silhouette-based synthetic data generation dedicated to this task, which enables us to bridge the domain gap between real-world data and synthetic data. We achieved higher estimation accuracy quantitatively and qualitatively compared with other baseline methods.
KW - 360 camera
KW - 3D human pose estimation
KW - Data synthesis
KW - Domain adaptation
KW - Silhouette
UR - http://www.scopus.com/inward/record.url?scp=85125586076&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85125586076&partnerID=8YFLogxK
U2 - 10.1109/ICIP42928.2021.9506043
DO - 10.1109/ICIP42928.2021.9506043
M3 - Conference contribution
AN - SCOPUS:85125586076
T3 - Proceedings - International Conference on Image Processing, ICIP
SP - 1304
EP - 1308
BT - 2021 IEEE International Conference on Image Processing, ICIP 2021 - Proceedings
PB - IEEE Computer Society
T2 - 2021 IEEE International Conference on Image Processing, ICIP 2021
Y2 - 19 September 2021 through 22 September 2021
ER -