Monocular 3D multi-person pose estimation via predicting factorized correction factors

• Published in: Computer vision and image understanding Vol. 213; p. 103278
• Main Authors: Guo, Yu, Ma, Lichen, Li, Zhi, Wang, Xuan, Wang, Fei
• Format: Journal Article
• Language: English
• Published: Elsevier Inc 01.12.2021
• Subjects: 3D human pose estimation; 3D localization of persons; Absolute depth estimation; Attention mechanism; Multi-person pose estimation; Top-down approach; Attention mechanism; 3D localization of persons; Top-down approach; Multi-person pose estimation; Absolute depth estimation; 3D human pose estimation
• ISSN: 1077-3142; 1090-235X
• DOI: 10.1016/j.cviu.2021.103278

Despite the great achievement of 3D human pose estimation, recovering the 3D poses of multiple persons in a single image is still a challenging problem. In this paper, we focus on one specific problem in 3D multi-person pose estimation (3D-MPPE): estimating the absolute 3D human poses. We proposed a pipeline consists of human detection, absolute 3D human root localization, and root-relative 3D single-person pose estimation modules. For the absolute 3D human root localization task, we propose a decoupling dual-branch structure to reconstruct the height of the human body, and further output the depth and localization of the 3D human root in the camera coordinate system. Furthermore, a data augmentation strategy is presented to tackle occlusions, such that our model can effectively estimate the root localization with the incomplete bounding boxes. For the 3D human relative pose estimation task, we use the attention mechanism to capture the correlation between human joint coordinates and further improve the accuracy of relative pose estimation. Finally, we merge the absolute depth of human and the relative 3D pose to output the absolute 3D human pose. •We improve the absolute human depth estimation via predicting factorised factors.•We exploit the data augmentation strategy to tackle the occlusions.•The attention mechanism for root-relative pose estimation is proposed.