HMOR: Hierarchical Multi-Person Ordinal Relations for Monocular Multi-Person 3D Pose Estimation
This addresses the problem of accurate and efficient 3D pose estimation for multiple people from single images, which is incremental but with strong performance gains.
The paper tackles 3D multi-person pose estimation from monocular RGB images by introducing Hierarchical Multi-person Ordinal Relations (HMOR) supervision to address global perspective limitations in top-down approaches, resulting in significantly outperforming state-of-the-art methods on public datasets with lower computation and fewer parameters.
Remarkable progress has been made in 3D human pose estimation from a monocular RGB camera. However, only a few studies explored 3D multi-person cases. In this paper, we attempt to address the lack of a global perspective of the top-down approaches by introducing a novel form of supervision - Hierarchical Multi-person Ordinal Relations (HMOR). The HMOR encodes interaction information as the ordinal relations of depths and angles hierarchically, which captures the body-part and joint level semantic and maintains global consistency at the same time. In our approach, an integrated top-down model is designed to leverage these ordinal relations in the learning process. The integrated model estimates human bounding boxes, human depths, and root-relative 3D poses simultaneously, with a coarse-to-fine architecture to improve the accuracy of depth estimation. The proposed method significantly outperforms state-of-the-art methods on publicly available multi-person 3D pose datasets. In addition to superior performance, our method costs lower computation complexity and fewer model parameters.