SOTAVerified

3D Multi-Person Pose Estimation

This task aims to solve root-relative 3D multi-person pose estimation. No human bounding box and root joint coordinate groundtruth are used in testing time.

( Image credit: RootNet )

Papers

Showing 1–10 of 62 papers

TitleStatusHype
Multi-person Physics-based Pose Estimation for Combat Sports—0
RapidPoseTriangulation: Multi-view Multi-person Whole-body Human Pose Triangulation in a MillisecondCode0
Multi-HMR: Multi-Person Whole-Body Human Mesh Recovery in a Single ShotCode3
Instance-aware Contrastive Learning for Occluded Human Mesh ReconstructionCode1
Geometry-Biased Transformer for Robust Multi-View 3D Human Pose Reconstruction—0
Towards Robust and Smooth 3D Multi-Person Pose Estimation from Monocular Videos in the Wild—0
Three Recipes for Better 3D Pseudo-GTs of 3D Human Mesh Estimation in the WildCode1
A Unified Multi-view Multi-person Tracking Framework—0
Weakly Supervised 3D Multi-person Pose Estimation for Large-scale Scenes based on Monocular Camera and Single LiDAR—0
Multi-Person 3D Pose and Shape Estimation via Inverse Kinematics and RefinementCode1
Show:102550
← PrevPage 1 of 7Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1TesseTrackPCP3D97.4—Unverified
2PlaneSweepPosePCP3D97—Unverified
3UMMTPCP3D97—Unverified
4SmartEdgeSensorPCP3D97—Unverified
5Faster VoxelPosePCP3D96.9—Unverified
6Part-aware PosePCP3D96.79—Unverified
7VoxelPosePCP3D96.7—Unverified
8VoxelTrackPCP3D96.7—Unverified
9crossview_3d_pose_trackingPCP3D96.6—Unverified
10Cross-ViewPCP3D96.6—Unverified