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
Neural Outlier Rejection for Self-Supervised Keypoint Learning
TRI-ML/KP2D
•
•
ICLR 2020
By making the sampling of inlier-outlier sets from point-pair correspondences fully differentiable within the keypoint learning framework, we show that are able to simultaneously self-supervise keypoint description and improve keypoint matching.
RelativeNAS: Relative Neural Architecture Search via Slow-Fast Learning
Despite the remarkable successes of Convolutional Neural Networks (CNNs) in computer vision, it is time-consuming and error-prone to manually design a CNN.
One Metric to Measure them All: Localisation Recall Precision (LRP) for Evaluating Visual Detection Tasks
Despite being widely used as a performance measure for visual detection tasks, Average Precision (AP) is limited in (i) reflecting localisation quality, (ii) interpretability and (iii) robustness to the design choices regarding its computation, and its applicability to outputs without confidence scores.
Regressive Domain Adaptation for Unsupervised Keypoint Detection
thuml/Regressive-Domain-Adaptation-for-Unsupervised-Keypoint-Detection
•
•
CVPR 2021
First, based on our observation that the probability density of the output space is sparse, we introduce a spatial probability distribution to describe this sparsity and then use it to guide the learning of the adversarial regressor.
End-to-End Trainable Multi-Instance Pose Estimation with Transformers
amathislab/poet
•
•
Inspired by recent work on end-to-end trainable object detection with transformers, we use a transformer encoder-decoder architecture together with a bipartite matching scheme to directly regress the pose of all individuals in a given image.
Bottom-Up Human Pose Estimation Via Disentangled Keypoint Regression
HRNet/DEKR
•
•
CVPR 2021
Our motivation is that regressing keypoint positions accurately needs to learn representations that focus on the keypoint regions.
DexYCB: A Benchmark for Capturing Hand Grasping of Objects
NVlabs/dex-ycb-toolkit
•
•
CVPR 2021
We introduce DexYCB, a new dataset for capturing hand grasping of objects.
Pose Recognition with Cascade Transformers
Here we utilize the encoder-decoder structure in Transformers to perform regression-based person and keypoint detection that is general-purpose and requires less heuristic design compared with the existing approaches.
MarkerPose: Robust Real-time Planar Target Tracking for Accurate Stereo Pose Estimation
In this work, we propose MarkerPose, a robust, real-time pose estimation system based on a planar target of three circles and a stereo vision system.
ALIKE: Accurate and Lightweight Keypoint Detection and Descriptor Extraction
Shiaoming/ALIKE
•
•
The reprojection loss is then proposed to directly optimize these sub-pixel keypoints, and the dispersity peak loss is presented for accurate keypoints regularization.
