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

Open Webpage

Yu Guo, Lichen Ma, Zhi Li, Xuan Wang, Fei Wang

Published: 2021, Last Modified: 11 Nov 2024Comput. Vis. Image Underst. 2021EveryoneRevisionsBibTeXCC BY-SA 4.0
Abstract: Highlights•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.