Multi-View Matching (MVM): Facilitating Multi-Person 3D Pose Estimation Learning with Action-Frozen People Video
This addresses the challenging problem of 3D pose estimation for computer vision applications, but it is incremental as it builds on existing multi-view and geometric constraint approaches.
The paper tackles multi-person 3D pose estimation from a single image by proposing a multi-view matching method that generates reliable 3D poses from action-frozen people videos, achieving state-of-the-art performance on 3DPW and MSCOCO datasets.
To tackle the challeging problem of multi-person 3D pose estimation from a single image, we propose a multi-view matching (MVM) method in this work. The MVM method generates reliable 3D human poses from a large-scale video dataset, called the Mannequin dataset, that contains action-frozen people immitating mannequins. With a large amount of in-the-wild video data labeled by 3D supervisions automatically generated by MVM, we are able to train a neural network that takes a single image as the input for multi-person 3D pose estimation. The core technology of MVM lies in effective alignment of 2D poses obtained from multiple views of a static scene that has a strong geometric constraint. Our objective is to maximize mutual consistency of 2D poses estimated in multiple frames, where geometric constraints as well as appearance similarities are taken into account simultaneously. To demonstrate the effectiveness of 3D supervisions provided by the MVM method, we conduct experiments on the 3DPW and the MSCOCO datasets and show that our proposed solution offers the state-of-the-art performance.