Pose Estimation
1339 papers with code • 28 benchmarks • 113 datasets
Pose Estimation is a computer vision task 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 )
Benchmarks
These leaderboards are used to track progress in Pose Estimation
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
Libraries
Use these libraries to find Pose Estimation models and implementations
MS COCO
KITTI
MPII
3DPW
AMASS
PASCAL3D+
JHMDB
DensePose
300W
LSP
Subtasks
-
3D Human Pose Estimation
-
Keypoint Detection
-
3D Pose Estimation
-
6D Pose Estimation
-
6D Pose Estimation
-
Hand Pose Estimation
-
6D Pose Estimation using RGB
-
Multi-Person Pose Estimation
-
Head Pose Estimation
-
Human Pose Forecasting
-
6D Pose Estimation using RGBD
-
Animal Pose Estimation
-
Vehicle Pose Estimation
-
RF-based Pose Estimation
-
Car Pose Estimation
-
Hand Joint Reconstruction
-
Activeness Detection
-
Semi-supervised 2D and 3D landmark labeling
Latest papers
KTPFormer: Kinematics and Trajectory Prior Knowledge-Enhanced Transformer for 3D Human Pose Estimation
This paper presents a novel Kinematics and Trajectory Prior Knowledge-Enhanced Transformer (KTPFormer), which overcomes the weakness in existing transformer-based methods for 3D human pose estimation that the derivation of Q, K, V vectors in their self-attention mechanisms are all based on simple linear mapping.
Video-Based Human Pose Regression via Decoupled Space-Time Aggregation
zgspose/dsta
•
•
In light of this, we propose a novel Decoupled Space-Time Aggregation network (DSTA) to separately capture the spatial contexts between adjacent joints and the temporal cues of each individual joint, thereby avoiding the conflation of spatiotemporal dimensions.
Instance-Adaptive and Geometric-Aware Keypoint Learning for Category-Level 6D Object Pose Estimation
(2) The second design is a Geometric-Aware Feature Aggregation module, which can efficiently integrate the local and global geometric information into keypoint features.
Object Pose Estimation via the Aggregation of Diffusion Features
To achieve this, we propose three distinct architectures that can effectively capture and aggregate diffusion features of different granularity, greatly improving the generalizability of object pose estimation.
A Survey on 3D Egocentric Human Pose Estimation
facebookresearch/xR-EgoPose
•
•
Egocentric human pose estimation aims to estimate human body poses and develop body representations from a first-person camera perspective.
GTA-HDR: A Large-Scale Synthetic Dataset for HDR Image Reconstruction
High Dynamic Range (HDR) content (i. e., images and videos) has a broad range of applications.
YOLOv5-6D: Advancing 6-DoF Instrument Pose Estimation in Variable X-Ray Imaging Geometries
cviviers/YOLOv5-6D-Pose
•
•
IEEE Transactions on Image Processing 2024
We propose a general-purpose approach of data acquisition for 6-DoF pose estimation tasks in X-ray systems, a novel and general purpose YOLOv5-6D pose architecture for accurate and fast object pose estimation and a complete method for surgical screw pose estimation under acquisition geometry consideration from a monocular cone-beam X-ray image.
DVMNet: Computing Relative Pose for Unseen Objects Beyond Hypotheses
sailor-z/dvmnet
•
•
Determining the relative pose of an object between two images is pivotal to the success of generalizable object pose estimation.
Meta-Point Learning and Refining for Category-Agnostic Pose Estimation
Existing methods only rely on the features extracted at support keypoints to predict or refine the keypoints on query image, but a few support feature vectors are local and inadequate for CAPE.
WHAC: World-grounded Humans and Cameras
In this study, we aim to recover expressive parametric human models (i. e., SMPL-X) and corresponding camera poses jointly, by leveraging the synergy between three critical players: the world, the human, and the camera.
