Pose Estimation

968 papers with code • 25 benchmarks • 109 datasets

Pose Estimation is a general problem in Computer Vision where the goal is to detect the position and orientation of a person or an object. Usually, this is done by predicting the location of specific keypoints like hands, head, elbows, etc. in case of Human Pose Estimation.

A common benchmark for this task is MPII Human Pose

( Image credit: Real-time 2D Multi-Person Pose Estimation on CPU: Lightweight OpenPose )


Use these libraries to find Pose Estimation models and implementations
31 papers
6 papers
See all 10 libraries.

Most implemented papers

Mask R-CNN

matterport/Mask_RCNN ICCV 2017

Our approach efficiently detects objects in an image while simultaneously generating a high-quality segmentation mask for each instance.

Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields

ZheC/Realtime_Multi-Person_Pose_Estimation CVPR 2017

We present an approach to efficiently detect the 2D pose of multiple people in an image.

Convolutional Pose Machines

CMU-Perceptual-Computing-Lab/convolutional-pose-machines-release CVPR 2016

Pose Machines provide a sequential prediction framework for learning rich implicit spatial models.

OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields

CMU-Perceptual-Computing-Lab/openpose 18 Dec 2018

OpenPose: Real-time multi-person keypoint detection library for body, face, hands, and foot estimation

Stacked Hourglass Networks for Human Pose Estimation

open-mmlab/mmpose 22 Mar 2016

This work introduces a novel convolutional network architecture for the task of human pose estimation.

High-Resolution Representations for Labeling Pixels and Regions

leoxiaobin/deep-high-resolution-net.pytorch 9 Apr 2019

The proposed approach achieves superior results to existing single-model networks on COCO object detection.

Deep High-Resolution Representation Learning for Human Pose Estimation

leoxiaobin/deep-high-resolution-net.pytorch CVPR 2019

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.

Deep High-Resolution Representation Learning for Visual Recognition

open-mmlab/mmdetection 20 Aug 2019

High-resolution representations are essential for position-sensitive vision problems, such as human pose estimation, semantic segmentation, and object detection.

Non-local Neural Networks

facebookresearch/video-nonlocal-net CVPR 2018

Both convolutional and recurrent operations are building blocks that process one local neighborhood at a time.

DensePose: Dense Human Pose Estimation In The Wild

facebookresearch/detectron CVPR 2018

In this work, we establish dense correspondences between RGB image and a surface-based representation of the human body, a task we refer to as dense human pose estimation.