Unsupervised Multi-Person 3D Human Pose Estimation From 2D Poses Alone
This work addresses the challenge of 3D pose estimation for multiple people in monocular images, which is incremental as it builds on prior unsupervised methods to handle multi-person scenarios.
The paper tackles the problem of unsupervised multi-person 3D human pose estimation from 2D poses alone, addressing perspective ambiguity in monocular images by predicting camera elevation angles to reconstruct human interactions, and it establishes a benchmark on the CHI3D dataset with new metrics.
Current unsupervised 2D-3D human pose estimation (HPE) methods do not work in multi-person scenarios due to perspective ambiguity in monocular images. Therefore, we present one of the first studies investigating the feasibility of unsupervised multi-person 2D-3D HPE from just 2D poses alone, focusing on reconstructing human interactions. To address the issue of perspective ambiguity, we expand upon prior work by predicting the cameras' elevation angle relative to the subjects' pelvis. This allows us to rotate the predicted poses to be level with the ground plane, while obtaining an estimate for the vertical offset in 3D between individuals. Our method involves independently lifting each subject's 2D pose to 3D, before combining them in a shared 3D coordinate system. The poses are then rotated and offset by the predicted elevation angle before being scaled. This by itself enables us to retrieve an accurate 3D reconstruction of their poses. We present our results on the CHI3D dataset, introducing its use for unsupervised 2D-3D pose estimation with three new quantitative metrics, and establishing a benchmark for future research.