SOTAVerified

3D Multi-Person Pose Estimation (absolute)

This task aims to solve absolute 3D multi-person pose Estimation (camera-centric coordinates). No ground truth human bounding box and human root joint coordinates are used during testing stage.

( Image credit: RootNet )

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–10 of 20 papers

TitleStatusHype
VirtualPose: Learning Generalizable 3D Human Pose Models from Virtual DataCode1
Dual networks based 3D Multi-Person Pose Estimation from Monocular VideoCode1
Distribution-Aware Single-Stage Models for Multi-Person 3D Pose EstimationCode1
Monocular 3D Multi-Person Pose Estimation by Integrating Top-Down and Bottom-Up NetworksCode1
Graph and Temporal Convolutional Networks for 3D Multi-person Pose Estimation in Monocular VideosCode1
SMAP: Single-Shot Multi-Person Absolute 3D Pose EstimationCode1
HDNet: Human Depth Estimation for Multi-Person Camera-Space LocalizationCode1
Multi-Person Absolute 3D Human Pose Estimation with Weak Depth SupervisionCode1
Towards Robust and Smooth 3D Multi-Person Pose Estimation from Monocular Videos in the Wild—0
Explicit Occlusion Reasoning for Multi-person 3D Human Pose Estimation—0
Show:102550
← PrevPage 1 of 2Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1Depth Prediction NetworkMPJPE292—Unverified
2Depth Prediction NetworkMPJPE120—Unverified
3VirtualPose3DPCK44—Unverified