HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimation

Code

• github.com/HRNet/Higher-HRNet-Human-Pose-Estimation
  OfficialIn paperpytorch★ 0
• github.com/PaddlePaddle/PaddleDetection
  paddle★ 14,132
• github.com/open-mmlab/mmpose
  pytorch★ 7,439
• github.com/ducongju/HRNet
  pytorch★ 1
• github.com/gox-ai/hrnet-pose-api
  pytorch★ 0
• github.com/visionNoob/hrnet_pytorch
  pytorch★ 0
• github.com/d-shivam/Pose-estimation-based-action-recognition-for-help-Situation-Identification
  pytorch★ 0
• github.com/code-implementation1/Code9/tree/main/hrnet
  mindspore★ 0
• github.com/Darius-Liesis/HRNet-works
  pytorch★ 0
• github.com/wsjzha/deep-high-resolution-net.pytorch
  pytorch★ 0

Abstract

Bottom-up human pose estimation methods have difficulties in predicting the correct pose for small persons due to challenges in scale variation. In this paper, we present HigherHRNet: a novel bottom-up human pose estimation method for learning scale-aware representations using high-resolution feature pyramids. Equipped with multi-resolution supervision for training and multi-resolution aggregation for inference, the proposed approach is able to solve the scale variation challenge in bottom-up multi-person pose estimation and localize keypoints more precisely, especially for small person. The feature pyramid in HigherHRNet consists of feature map outputs from HRNet and upsampled higher-resolution outputs through a transposed convolution. HigherHRNet outperforms the previous best bottom-up method by 2.5% AP for medium person on COCO test-dev, showing its effectiveness in handling scale variation. Furthermore, HigherHRNet achieves new state-of-the-art result on COCO test-dev (70.5% AP) without using refinement or other post-processing techniques, surpassing all existing bottom-up methods. HigherHRNet even surpasses all top-down methods on CrowdPose test (67.6% AP), suggesting its robustness in crowded scene. The code and models are available at https://github.com/HRNet/Higher-HRNet-Human-Pose-Estimation.

Tasks

Benchmark Results

Reproductions