2D Human Pose Estimation

63 papers with code • 5 benchmarks • 22 datasets

What is Human Pose Estimation? Human pose estimation is the process of estimating the configuration of the body (pose) from a single, typically monocular, image. Background. Human pose estimation is one of the key problems in computer vision that has been studied for well over 15 years. The reason for its importance is the abundance of applications that can benefit from such a technology. For example, human pose estimation allows for higher-level reasoning in the context of human-computer interaction and activity recognition; it is also one of the basic building blocks for marker-less motion capture (MoCap) technology. MoCap technology is useful for applications ranging from character animation to clinical analysis of gait pathologies.

Libraries

Use these libraries to find 2D Human Pose Estimation models and implementations

Most implemented papers

ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation

vitae-transformer/vitpose 26 Apr 2022

In this paper, we show the surprisingly good capabilities of plain vision transformers for pose estimation from various aspects, namely simplicity in model structure, scalability in model size, flexibility in training paradigm, and transferability of knowledge between models, through a simple baseline model called ViTPose.

Explicit Box Detection Unifies End-to-End Multi-Person Pose Estimation

idea-research/ed-pose 3 Feb 2023

This paper presents a novel end-to-end framework with Explicit box Detection for multi-person Pose estimation, called ED-Pose, where it unifies the contextual learning between human-level (global) and keypoint-level (local) information.

Preconditioned Stochastic Gradient Descent

lixilinx/psgd_torch 14 Dec 2015

When stochastic gradient is used, it can naturally damp the gradient noise to stabilize SGD.

Learning from Synthetic Humans

gulvarol/surreal CVPR 2017

In this work we present SURREAL (Synthetic hUmans foR REAL tasks): a new large-scale dataset with synthetically-generated but realistic images of people rendered from 3D sequences of human motion capture data.

PifPaf: Composite Fields for Human Pose Estimation

thanhtrung98/human_pose_estimation CVPR 2019

We propose a new bottom-up method for multi-person 2D human pose estimation that is particularly well suited for urban mobility such as self-driving cars and delivery robots.

Whole-Body Human Pose Estimation in the Wild

jin-s13/COCO-WholeBody ECCV 2020

This paper investigates the task of 2D human whole-body pose estimation, which aims to localize dense landmarks on the entire human body including face, hands, body, and feet.

Scalable Hierarchical Agglomerative Clustering

nmonath/scc 22 Oct 2020

The applicability of agglomerative clustering, for inferring both hierarchical and flat clustering, is limited by its scalability.

Estimating Parkinsonism Severity in Natural Gait Videos of Older Adults with Dementia

TaatiTeam/stgcn_parkinsonism_prediction 7 May 2021

This work leverages novel spatial-temporal graph convolutional network (ST-GCN) architectures and training procedures to predict clinical scores of parkinsonism in gait from video of individuals with dementia.

Event Neural Networks

WISION-Lab/event-nn-tf 2 Dec 2021

Video data is often repetitive; for example, the contents of adjacent frames are usually strongly correlated.