Multi-person 3D human pose estimation from a single image is a challenging
problem, especially for in-the-wild settings due to the lack of 3D annotated
data. We propose HG-RCNN, a Mask-RCNN based network that also leverages the
benefits of the Hourglass architecture for multi-person 3D Human Pose
Estimation. A two-staged approach is presented that first estimates the 2D
keypoints in every Region of Interest (RoI) and then lifts the estimated
keypoints to 3D. Finally, the estimated 3D poses are placed in
camera-coordinates using weak-perspective projection assumption and joint
optimization of focal length and root translations. The result is a simple and
modular network for multi-person 3D human pose estimation that does not require
any multi-person 3D pose dataset. Despite its simple formulation, HG-RCNN
achieves the state-of-the-art results on MuPoTS-3D while also approximating the
3D pose in the camera-coordinate system.

通过提出的 HG-RCNN 网络，借助 Mask-RCNN 和 Hourglass 结构进行多人 3D 人体姿态估计，实现对每个感兴趣区域（RoI）中 2D 关键点的先预测后提升，最终采用弱透视投影模型和焦距和根偏移的联合优化将估计的 3D 姿态置于相机坐标系下，该网络简单模块化且无需多人 3D 姿态数据集，取得了 MuPoTS-3D 数据集的最优性能，并能近似在相机坐标系下估计 3D 姿态。

从单目图像估计多人三维人体姿态

Multi-Person 3D Human Pose Estimation from Monocular Images

This paper proposes a new Generative Partition Network (GPN) to address the
challenging multi-person pose estimation problem. Different from existing
models that are either completely top-down or bottom-up, the proposed GPN
introduces a novel strategy--it generates partitions for multiple persons from
their global joint candidates and infers instance-specific joint configurations
simultaneously. The GPN is favorably featured by low complexity and high
accuracy of joint detection and re-organization. In particular, GPN designs a
generative model that performs one feed-forward pass to efficiently generate
robust person detections with joint partitions, relying on dense regressions
from global joint candidates in an embedding space parameterized by centroids
of persons. In addition, GPN formulates the inference procedure for joint
configurations of human poses as a graph partition problem, and conducts local
optimization for each person detection with reliable global affinity cues,
leading to complexity reduction and performance improvement. GPN is implemented
with the Hourglass architecture as the backbone network to simultaneously learn
joint detector and dense regressor. Extensive experiments on benchmarks MPII
Human Pose Multi-Person, extended PASCAL-Person-Part, and WAF, show the
efficiency of GPN with new state-of-the-art performance.

该论文提出了一种新的生成式分区网络 (GPN)，旨在解决复杂的多人姿态估计问题，其引入了一种从全局关节点生成多人分区的新策略，并同时推断实例特定的关节配置。GPN 是低复杂度和高联合检测的准确性的有益特点，它在 MPII Human Pose Multi-Person，扩展的 PASCAL-Person-Part 和 WAF 基准测试上产生了新的最先进性能。