Startseite Neuigkeiten Neueste Forschungsarbeiten Tutorials Datensätze Wiki SOTA LLM-Modelle GPU-Rangliste Veranstaltungen

Deutsch

3D Multi Person Pose Estimation On Campus

Metriken

Mean mAP

PCP3D

Ergebnisse

Leistungsergebnisse verschiedener Modelle zu diesem Benchmark

Modellname	Mean mAP	PCP3D	Paper Title	Repository
VTP	80.1	96.3	VTP: Volumetric Transformer for Multi-view Multi-person 3D Pose Estimation	-
TesseTrack	-	97.4	TesseTrack: End-to-End Learnable Multi-Person Articulated 3D Pose Tracking	-
PlaneSweepPose	-	97	Multi-View Multi-Person 3D Pose Estimation with Plane Sweep Stereo
Ershadi-Nasab model	-	90.6	Multiple human 3d pose estimation from multiview images	-
MvP	-	96.6	Direct Multi-view Multi-person 3D Pose Estimation
MVPose	-	96.3	Fast and Robust Multi-Person 3D Pose Estimation from Multiple Views
Faster VoxelPose	-	96.9	Faster VoxelPose: Real-time 3D Human Pose Estimation by Orthographic Projection
VoxelTrack	-	96.7	VoxelTrack: Multi-Person 3D Human Pose Estimation and Tracking in the Wild	-
Belagiannis model v.3	-	84.5	3D Pictorial Structures Revisited: Multiple Human Pose Estimation	-
Belagiannis model v.2	-	78	Multiple human pose estimation with temporally consistent 3d pictorial structures	-
SmartEdgeSensor	-	97	Real-Time Multi-View 3D Human Pose Estimation using Semantic Feedback to Smart Edge Sensors
Part-aware Pose	-	96.79	Part-Aware Measurement for Robust Multi-View Multi-Human 3D Pose Estimation and Tracking
VoxelPose	-	96.7	VoxelPose: Towards Multi-Camera 3D Human Pose Estimation in Wild Environment
UMMT	-	97.0	A Unified Multi-view Multi-person Tracking Framework	-
Cross-View	-	96.6	Cross-View Tracking for Multi-Human 3D Pose Estimation at over 100 FPS
crossview_3d_pose_tracking	-	96.6	Cross-View Tracking for Multi-Human 3D Pose Estimation at over 100 FPS

0 of 16 row(s) selected.