Deep High-Resolution Representation Learning for Human Pose Estimation

Code

• github.com/Microsoft/human-pose-estimation.pytorch
  OfficialIn paperpytorch★ 0
• github.com/leoxiaobin/deep-high-resolution-net.pytorch
  OfficialIn paperpytorch★ 0
• github.com/open-mmlab/mmdetection
  pytorch★ 32,525
• github.com/PaddlePaddle/PaddleDetection
  paddle★ 14,132
• github.com/open-mmlab/mmpose
  pytorch★ 7,439
• github.com/osmr/imgclsmob
  mxnet★ 3,015
• github.com/mindspore-lab/mindone
  mindspore★ 464
• github.com/leeyegy/simcc
  pytorch★ 340
• github.com/leeyegy/SimDR
  pytorch★ 340
• github.com/CASIA-IVA-Lab/ISP-reID
  pytorch★ 95

Abstract

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

Tasks

Benchmark Results

Reproductions