Unite the People 3D 人体模型数据集

Unite The People 是一个用于 3D 人体姿态估计的图像数据集。这些图像来自 Leeds Sports Pose 数据集和它的扩展版，以及 MPII 人体姿势数据集。每张图像有不同类型的标注，如分割标签、姿势或 3D，图像中的人体模型被分为 31 个部位和 91 个关键点。

Unite The People is an image dataset dedicated to 3D human pose estimation. The images are sourced from the Leeds Sports Pose dataset and its extended version, as well as the MPII Human Pose dataset. Each image is equipped with multiple types of annotations, including segmentation labels, pose annotations, and 3D annotations. The human body models depicted in the images are divided into 31 body parts and annotated with 91 keypoints.

搜集汇总

背景与挑战

背景概述

Unite the People是一个专用于3D人体姿态估计的图像数据集，整合了来自Leeds Sports Pose和MPII数据集的图像，并提供分割标签、姿势及3D标注，将人体模型划分为31个部位和91个关键点。该数据集可用于支持人体姿态估计研究，并训练2D人体姿态估计器。