BlazePose GHUM Holistic：实时三维人体关键点与姿态估计
计算机视觉与模式识别
2022-06-24 v1
摘要
我们提出 BlazePose GHUM Holistic，一种轻量级神经网络流水线，用于三维人体关键点与姿态估计，特别为实时端上推理而设计。BlazePose GHUM Holistic 可从单张 RGB 图像实现动作捕捉，包括虚拟形象控制、健身追踪和 AR/VR 效果。我们的主要贡献包括：i）一种获取三维真值数据的新方法；ii）带有额外手部关键点的更新三维身体追踪；iii）从单目图像进行全身姿态估计。
引用
@article{arxiv.2206.11678,
title = {BlazePose GHUM Holistic: Real-time 3D Human Landmarks and Pose Estimation},
author = {Ivan Grishchenko and Valentin Bazarevsky and Andrei Zanfir and Eduard Gabriel Bazavan and Mihai Zanfir and Richard Yee and Karthik Raveendran and Matsvei Zhdanovich and Matthias Grundmann and Cristian Sminchisescu},
journal= {arXiv preprint arXiv:2206.11678},
year = {2022}
}
备注
4 pages, 4 figures; CVPR Workshop on Computer Vision for Augmented and Virtual Reality, New Orleans, LA, 2022