Deep Learning-based Human Pose Estimation: A Survey (2020-12-24T00:00:00.000000Z)

TL;DR

This survey article is to provide a comprehensive review of recent deep learning-based solutions for both 2D and 3D pose estimation via a systematic analysis and comparison of these solutions based on their input data and inference procedures.

Abstract

Human pose estimation aims to locate the human body parts and build human body representation (e.g., body skeleton) from input data such as images and videos. It has drawn increasing attention during the past decade and has been utilized in a wide range of applications including human-computer interaction, motion analysis, augmented reality, and virtual reality. Although the recently developed deep learning-based solutions have achieved high performance in human pose estimation, there still remain challenges due to insufficient training data, depth ambiguities, and occlusion. The goal of this survey article is to provide a comprehensive review of recent deep learning-based solutions for both 2D and 3D pose estimation via a systematic analysis and comparison of these solutions based on their input data and inference procedures. More than 260 research papers since 2014 are covered in this survey. Furthermore, 2D and 3D human pose estimation datasets and evaluation metrics are included. Quantitative performance comparisons of the reviewed methods on popular datasets are summarized and discussed. Finally, the challenges involved, applications, and future research directions are concluded. A regularly updated project page is provided: https://github.com/zczcwh/DL-HPE.

Authors

N. Kehtarnavaz

2 papers

Ce Zheng

2 papers

Wenhan Wu

1 papers

TL;DR

Abstract

Authors

References362 items

SMPL: A Skinned Multi-Person Linear Model

Part Aware Contrastive Learning for Self-Supervised Action Recognition

PoseFormerV2: Exploring Frequency Domain for Efficient and Robust 3D Human Pose Estimation

POTTER: Pooling Attention Transformer for Efficient Human Mesh Recovery

PPT: token-Pruned Pose Transformer for monocular and multi-view human pose estimation

Cross-Attention of Disentangled Modalities for 3D Human Mesh Recovery with Transformers

Faster VoxelPose: Real-time 3D Human Pose Estimation by Orthographic Projection

End-to-End Multi-Person Pose Estimation with Transformers

FeatER: An Efficient Network for Human Reconstruction via Feature Map-Based TransformER

Lite Pose: Efficient Architecture Design for 2D Human Pose Estimation

Temporal Feature Alignment and Mutual Information Maximization for Video-Based Human Pose Estimation

Distribution-Aware Single-Stage Models for Multi-Person 3D Pose Estimation

MixSTE: Seq2seq Mixed Spatio-Temporal Encoder for 3D Human Pose Estimation in Video

Poseur: Direct Human Pose Regression with Transformers

PE-former: Pose Estimation Transformer

A Lightweight Graph Transformer Network for Human Mesh Reconstruction from 2D Human Pose

MHFormer: Multi-Hypothesis Transformer for 3D Human Pose Estimation

TransFusion: Cross-view Fusion with Transformer for 3D Human Pose Estimation

Shape-aware Multi-Person Pose Estimation from Multi-View Images

Modulated Graph Convolutional Network for 3D Human Pose Estimation

GraFormer: Graph Convolution Transformer for 3D Pose Estimation

Probabilistic Modeling for Human Mesh Recovery

Human Pose Regression with Residual Log-likelihood Estimation

SimCC: A Simple Coordinate Classification Perspective for Human Pose Estimation

Test-Time Personalization with a Transformer for Human Pose Estimation

Polarized Self-Attention: Towards High-quality Pixel-wise Regression

TesseTrack: End-to-End Learnable Multi-Person Articulated 3D Pose Tracking

ViPNAS: Efficient Video Pose Estimation via Neural Architecture Search

Pose Recognition with Cascade Transformers

Lite-HRNet: A Lightweight High-Resolution Network

TokenPose: Learning Keypoint Tokens for Human Pose Estimation

Monocular 3D Multi-Person Pose Estimation by Integrating Top-Down and Bottom-Up Networks

Mesh Graphormer

PyMAF: 3D Human Pose and Shape Regression with Pyramidal Mesh Alignment Feedback Loop

TFPose: Direct Human Pose Estimation with Transformers

Exploiting Temporal Contexts With Strided Transformer for 3D Human Pose Estimation

3D Human Pose Estimation with Spatial and Temporal Transformers

Deep Dual Consecutive Network for Human Pose Estimation

Anatomy-Aware 3D Human Pose Estimation With Bone-Based Pose Decomposition

Transformers in Vision: A Survey

Rethinking the Heatmap Regression for Bottom-up Human Pose Estimation

TransPose: Keypoint Localization via Transformer

Graph and Temporal Convolutional Networks for 3D Multi-person Pose Estimation in Monocular Videos

End-to-End Human Pose and Mesh Reconstruction with Transformers

EfficientPose: Efficient human pose estimation with neural architecture search

A novel joint points and silhouette-based method to estimate 3D human pose and shape

Enhancing Human Pose Estimation in Ancient Vase Paintings via Perceptually-grounded Style Transfer Learning

A survey on monocular 3D human pose estimation

HybrIK: A Hybrid Analytical-Neural Inverse Kinematics Solution for 3D Human Pose and Shape Estimation

Beyond Static Features for Temporally Consistent 3D Human Pose and Shape from a Video

AdaFuse: Adaptive Multiview Fusion for Accurate Human Pose Estimation in the Wild

PoseTween: Pose-driven Tween Animation

Invariant Representation Learning for Infant Pose Estimation with Small Data

SelfPose: 3D Egocentric Pose Estimation From a Headset Mounted Camera

Orientation Keypoints for 6D Human Pose Estimation

SMAP: Single-Shot Multi-Person Absolute 3D Pose Estimation

BLSM: A Bone-Level Skinned Model of the Human Mesh

Towards Part-Aware Monocular 3D Human Pose Estimation: An Architecture Search Approach

A Comprehensive Study of Weight Sharing in Graph Networks for 3D Human Pose Estimation

Pose2Mesh: Graph Convolutional Network for 3D Human Pose and Mesh Recovery from a 2D Human Pose

STAR: Sparse Trained Articulated Human Body Regressor

AutoPose: Searching Multi-Scale Branch Aggregation for Pose Estimation

Vid2Player: Controllable Video Sprites That Behave and Appear Like Professional Tennis Players

I2L-MeshNet: Image-to-Lixel Prediction Network for Accurate 3D Human Pose and Mesh Estimation from a Single RGB Image

Unsupervised Cross-Modal Alignment for Multi-Person 3D Pose Estimation

Appearance Consensus Driven Self-Supervised Human Mesh Recovery

TexMesh: Reconstructing Detailed Human Texture and Geometry from RGB-D Video

HMOR: Hierarchical Multi-Person Ordinal Relations for Monocular Multi-Person 3D Pose Estimation

Key Frame Proposal Network for Efficient Pose Estimation in Videos

Reconstructing NBA Players

3D Human Shape and Pose from a Single Low-Resolution Image with Self-Supervised Learning

Differentiable Hierarchical Graph Grouping for Multi-Person Pose Estimation

Whole-Body Human Pose Estimation in the Wild

Unsupervised Shape and Pose Disentanglement for 3D Meshes

Multi-person 3D Pose Estimation in Crowded Scenes Based on Multi-View Geometry

Graph-PCNN: Two Stage Human Pose Estimation with Graph Pose Refinement