RePOSE : 3D human pose estimation via spatio-temporal depth relational consistency

• Main Authors: SUN, Ziming, LIANG, Yuan, MA, Zejun, ZHANG, Tianle, BAO, Linchao, LI, Guiqing, HE, Shengfeng
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2024
• Subjects: 3D human pose estimation; Depth relational loss functions; Databases and Information Systems; Graphics and Human Computer Interfaces
• Online Access: https://ink.library.smu.edu.sg/sis_research/9803
• Institution: Singapore Management University

We introduce RePOSE, a simple yet effective approach for addressing occlusion challenges in the learning of 3D human pose estimation (HPE) from videos. Conventional approaches typically employ absolute depth signals as supervision, which are adept at discernible keypoints but become less reliable wh...