SOTAVerified

Pose Estimation

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 )

Papers

Showing 110 of 4228 papers

TitleStatusHype
From Neck to Head: Bio-Impedance Sensing for Head Pose Estimation0
DINO-VO: A Feature-based Visual Odometry Leveraging a Visual Foundation Model0
AthleticsPose: Authentic Sports Motion Dataset on Athletic Field and Evaluation of Monocular 3D Pose Estimation AbilityCode0
π^3: Scalable Permutation-Equivariant Visual Geometry Learning0
Revisiting Reliability in the Reasoning-based Pose Estimation Benchmark0
BRUM: Robust 3D Vehicle Reconstruction from 360 Sparse Images0
SEPose: A Synthetic Event-based Human Pose Estimation Dataset for Pedestrian Monitoring0
SGLoc: Semantic Localization System for Camera Pose Estimation from 3D Gaussian Splatting RepresentationCode0
Efficient Calisthenics Skills Classification through Foreground Instance Selection and Depth EstimationCode0
SpatialTrackerV2: 3D Point Tracking Made EasyCode4
Show:102550
← PrevPage 1 of 423Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1yoloposeAP5090.3Unverified
2ViTPose (ViTAE-G, ensemble)AP81.1Unverified
3ViTPose (ViTAE-G)AP80.9Unverified
4UDP-Pose-PSA(384x288)AP79.5Unverified
5PoseBH-HAP79.5Unverified
64xRSN-50 (ensemble)AP79.2Unverified
7CCM+AP78.9Unverified
8UDP-Pose-PSA(256x192)AP78.9Unverified
94xRSN-50AP78.6Unverified
10PCT (256x256)AP78.3Unverified