Multi-person 3D pose estimation from unlabelled data

arXiv:2212.08731v3 Announce Type: replace
Abstract: Its numerous applications make multi-human 3D pose estimation a remarkably impactful area of research. Nevertheless, assuming a multiple-view system composed of several regular RGB cameras, 3D multi-pose estimation presents several challenges. First of all, each person must be uniquely identified in the different views to separate the 2D information provided by the cameras. Secondly, the 3D pose estimation process from the multi-view 2D information of each person must be robust against noise and potential occlusions …

abstract applications arxiv cameras challenges cs.ai cs.cv data human multiple person research type view