Deep High-Resolution Representation Learning for Human Pose Estimation

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

accepted by CVPR2019

References in corpus (13)

• DeepPose: Human Pose Estimation via Deep Neural Networks
• MOT16: A Benchmark for Multi-Object Tracking
• Joint Training of a Convolutional Network and a Graphical Model for Human Pose Estimation
• Associative Embedding: End-to-End Learning for Joint Detection and Grouping
• Human pose estimation via Convolutional Part Heatmap Regression
• Articulated Pose Estimation by a Graphical Model with Image Dependent Pairwise Relations
• AI Challenger : A Large-scale Dataset for Going Deeper in Image Understanding
• Cascaded Pyramid Network for Multi-Person Pose Estimation
• Locally Scale-Invariant Convolutional Neural Networks
• Scale-Invariant Convolutional Neural Networks
• Interlinked Convolutional Neural Networks for Face Parsing
• Jointly Optimize Data Augmentation and Network Training: Adversarial Data Augmentation in Human Pose Estimation
• Self Adversarial Training for Human Pose Estimation

Cited by in corpus (30)

• MoVi: A Large Multipurpose Motion and Video Dataset
• FasterSeg: Searching for Faster Real-time Semantic Segmentation
• Rethinking on Multi-Stage Networks for Human Pose Estimation
• Movement science needs different pose tracking algorithms
• SolarNet: A Deep Learning Framework to Map Solar Power Plants In China From Satellite Imagery
• Attention-guided Chained Context Aggregation for Semantic Segmentation
• Face X-ray for More General Face Forgery Detection
• Differentiable Hierarchical Graph Grouping for Multi-Person Pose Estimation
• Efficient Differentiable Neural Architecture Search with Meta Kernels
• High-Resolution Network for Photorealistic Style Transfer
• Multi-Stage HRNet: Multiple Stage High-Resolution Network for Human Pose Estimation
• End-to-End Trainable Multi-Instance Pose Estimation with Transformers
• Lightweight Multi-View 3D Pose Estimation through Camera-Disentangled Representation
• Self-Supervised 3D Keypoint Learning for Ego-motion Estimation
• When Human Pose Estimation Meets Robustness: Adversarial Algorithms and Benchmarks
• Rotation-invariant Mixed Graphical Model Network for 2D Hand Pose Estimation
• Hybrid Composition with IdleBlock: More Efficient Networks for Image Recognition
• FlatteNet: A Simple Versatile Framework for Dense Pixelwise Prediction
• Anti-Confusing: Region-Aware Network for Human Pose Estimation
• Whole-Body Human Pose Estimation in the Wild
• Augmented Parallel-Pyramid Net for Attention Guided Pose-Estimation
• Adversarial Semantic Data Augmentation for Human Pose Estimation
• High Frequency Residual Learning for Multi-Scale Image Classification
• Correlating Edge, Pose with Parsing
• Unposed: Unsupervised Pose Estimation based Product Image Recommendations
• Discriminative and Semantic Feature Selection for Place Recognition towards Dynamic Environments
• Human Keypoint Detection by Progressive Context Refinement
• FollowMeUp Sports: New Benchmark for 2D Human Keypoint Recognition
• An End-to-End Framework for Unsupervised Pose Estimation of Occluded Pedestrians
• $P^2$ Net: Augmented Parallel-Pyramid Net for Attention Guided Pose Estimation