HRNet：Deep High-Resolution Representation Learning for Human Pose Estimation

This is an official pytorch implementation of Deep High-Resolution Representation Learning for Human Pose Estimation. In this work, we are interested in the human pose estimation problem with a focus on learning reliable high-resolution representations. Most existing methods recover high-resolution representations from low-resolution representations produced by a high-to-low resolution network. Instead, our proposed network maintains high-resolution representations through the whole process. We start from a high-resolution subnetwork as the first stage, gradually add high-to-low resolution subnetworks one by one to form more stages, and connect the mutli-resolution subnetworks in parallel. We conduct repeated multi-scale fusions such that each of the high-to-low resolution representations receives information from other parallel representations over and over, leading to rich high-resolution representations. As a result, the predicted keypoint heatmap is potentially more accurate and spatially more precise. We empirically demonstrate the effectiveness of our network through the superior pose estimation results over two benchmark datasets: the COCO keypoint detection dataset and the MPII Human Pose dataset. The code and models have been publicly available at \url{this https URL}.

论文下载

论文地址：https://arxiv.org/abs/1902.09212

算法链接

算法：https://marketplace.huaweicloud.com/markets/aihub/modelhub/detail/?id=f5264a0c-31b7-4cfd-8a22-48010860a41c

算法指南

算法指南：https://bbs.huaweicloud.com/forum/forum.php?mod=viewthread&tid=93586&page=1