Deep High-Resolution Representation Learning for Human Pose Estimation

CVPR 2019  ·  Ke Sun, Bin Xiao, Dong Liu, Jingdong Wang ·

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{https://github.com/leoxiaobin/deep-high-resolution-net.pytorch}.

PDF Abstract CVPR 2019 PDF CVPR 2019 Abstract

Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Keypoint Detection COCO HRNet-32 Validation AP 75.8 # 8
Keypoint Detection COCO HRNet-48(384x288) Validation AP 76.3 # 6
Test AP 75.5 # 9
Instance Segmentation COCO minival HTC (HRNetV2p-W48) mask AP 41.0 # 40
Keypoint Detection COCO test-dev HRNet* APL 83.1 # 1
APM 73.4 # 1
AP50 92.7 # 2
AP75 84.5 # 1
AR 82.0 # 1
Keypoint Detection COCO test-dev HRNet APL 81.5 # 3
APM 71.9 # 4
AP50 92.5 # 3
AP75 83.3 # 4
AR 80.5 # 4
Pose Estimation COCO test-dev HRNet-W48 + extra data AP 77 # 8
AP50 92.7 # 8
AP75 84.5 # 8
APL 83.1 # 6
APM 73.4 # 10
AR 82 # 7
2D Human Pose Estimation COCO-WholeBody HRNet WB 43.2 # 3
body 65.9 # 3
foot 31.4 # 5
face 52.3 # 4
hand 30.0 # 5
Pose Estimation MPII Human Pose HRNet-W32 PCKh-0.5 92.3% # 7
Pose Tracking PoseTrack2017 HRNet-W48 COCO MOTA 57.93 # 4
mAP 74.95 # 1

Methods