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 )
|TREND||DATASET||BEST METHOD||PAPER TITLE||PAPER||CODE||COMPARE|
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.
#7 best model for Keypoint Detection on COCO
Our method uses entire face images at all stages, contrary to the recently proposed face alignment methods that rely on local patches.
#7 best model for Face Alignment on 300W
In this paper, we present MultiPoseNet, a novel bottom-up multi-person pose estimation architecture that combines a multi-task model with a novel assignment method.
#4 best model for Multi-Person Pose Estimation on COCO
Existing pose estimation approaches fall into two categories: single-stage and multi-stage methods.
#3 best model for Keypoint Detection on COCO
In this paper, we propose a human pose refinement network that estimates a refined pose from a tuple of an input image and input pose.
SOTA for Multi-Person Pose Estimation on COCO (Validation AP metric )
In this paper, we propose a novel and efficient method to tackle the problem of pose estimation in the crowd and a new dataset to better evaluate algorithms.
#2 best model for Multi-Person Pose Estimation on CrowdPose
Interestingly, we found that the process of decoding the predicted heatmaps into the final joint coordinates in the original image space is surprisingly significant for human pose estimation performance, which nevertheless was not recognised before.
SOTA for Pose Estimation on COCO (using extra training data)
Keypoint detection usually results in a large number of keypoints which are mostly clustered, redundant, and noisy.