Keypoint Detection
150 papers with code • 7 benchmarks • 11 datasets
Keypoint Detection involves simultaneously detecting people and localizing their keypoints. Keypoints are the same thing as interest points. They are spatial locations, or points in the image that define what is interesting or what stand out in the image. They are invariant to image rotation, shrinkage, translation, distortion, and so on.
( Image credit: PifPaf: Composite Fields for Human Pose Estimation; "Learning to surf" by fotologic, license: CC-BY-2.0 )
Benchmarks
These leaderboards are used to track progress in Keypoint Detection
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
Libraries
Use these libraries to find Keypoint Detection models and implementationsDatasets
MS COCO
MPII
PASCAL3D+
OCHuman
KeypointNet
ApolloCar3D
GRIT
AwA Pose
TAMPAR
RadioGalaxyNET Dataset
Most implemented papers
Mask R-CNN
tensorflow/models
•
•
ICCV 2017
Our approach efficiently detects objects in an image while simultaneously generating a high-quality segmentation mask for each instance.
Objects as Points
We model an object as a single point --- the center point of its bounding box.
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.
OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields
CMU-Perceptual-Computing-Lab/openpose
•
•
OpenPose: Real-time multi-person keypoint detection library for body, face, hands, and foot estimation
Hand Keypoint Detection in Single Images using Multiview Bootstrapping
CMU-Perceptual-Computing-Lab/openpose
•
•
CVPR 2017
The method is used to train a hand keypoint detector for single images.
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.
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.
Simple Baselines for Human Pose Estimation and Tracking
leoxiaobin/pose.pytorch
•
•
ECCV 2018
There has been significant progress on pose estimation and increasing interests on pose tracking in recent years.
DeeperCut: A Deeper, Stronger, and Faster Multi-Person Pose Estimation Model
The goal of this paper is to advance the state-of-the-art of articulated pose estimation in scenes with multiple people.
RMPE: Regional Multi-person Pose Estimation
MVIG-SJTU/AlphaPose
•
•
ICCV 2017
In this paper, we propose a novel regional multi-person pose estimation (RMPE) framework to facilitate pose estimation in the presence of inaccurate human bounding boxes.
