SOTAVerified

3D Human Pose Estimation

3D Human Pose Estimation is a computer vision task that involves estimating the 3D positions and orientations of body joints and bones from 2D images or videos. The goal is to reconstruct the 3D pose of a person in real-time, which can be used in a variety of applications, such as virtual reality, human-computer interaction, and motion analysis.

Papers

Showing 526550 of 665 papers

TitleStatusHype
mRI: Multi-modal 3D Human Pose Estimation Dataset using mmWave, RGB-D, and Inertial Sensors0
MUG: Multi-human Graph Network for 3D Mesh Reconstruction from 2D Pose0
Multi-hop graph transformer network for 3D human pose estimation0
Multi-initialization Optimization Network for Accurate 3D Human Pose and Shape Estimation0
Multi-modal 3D Human Pose Estimation with 2D Weak Supervision in Autonomous Driving0
Multi-modal Pose Diffuser: A Multimodal Generative Conditional Pose Prior0
Multi-Person 3D Human Pose Estimation from Monocular Images0
Multi-person 3D pose estimation from a single image captured by a fisheye camera0
Multi-Person 3D Pose Estimation from Multi-View Uncalibrated Depth Cameras0
Multi-person Physics-based Pose Estimation for Combat Sports0
Multi-Scale Networks for 3D Human Pose Estimation with Inference Stage Optimization0
Multi-View Matching (MVM): Facilitating Multi-Person 3D Pose Estimation Learning with Action-Frozen People Video0
Multi-View Person Matching and 3D Pose Estimation with Arbitrary Uncalibrated Camera Networks0
Mirror-Aware Neural HumansCode0
Regular Splitting Graph Network for 3D Human Pose EstimationCode0
Monocular Total Capture: Posing Face, Body, and Hands in the WildCode0
MHEntropy: Entropy Meets Multiple Hypotheses for Pose and Shape RecoveryCode0
MetaPose: Fast 3D Pose from Multiple Views without 3D SupervisionCode0
Synthetic Occlusion Augmentation with Volumetric Heatmaps for the 2018 ECCV PoseTrack Challenge on 3D Human Pose EstimationCode0
Measuring Physical Plausibility of 3D Human Poses Using Physics SimulationCode0
Adapted Human Pose: Monocular 3D Human Pose Estimation with Zero Real 3D Pose DataCode0
RepNet: Weakly Supervised Training of an Adversarial Reprojection Network for 3D Human Pose EstimationCode0
Unsupervised Cross-Modal Alignment for Multi-Person 3D Pose EstimationCode0
MPT: Mesh Pre-Training with Transformers for Human Pose and Mesh ReconstructionCode0
Decanus to Legatus: Synthetic training for 2D-3D human pose liftingCode0
Show:102550
← PrevPage 22 of 27Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1Simple-baselinePA-MPJPE157Unverified
2HMRMPJPE130Unverified
3BMPMPVPE119.3Unverified
4SPINMPVPE116.4Unverified
5Wenshuo et a;.MPVPE112.6Unverified
6TCMR (T=16 w/o 3DPW)MPVPE111.5Unverified
7CHOMPMPVPE110.1Unverified
8PC-HMRMPVPE108.6Unverified
93DCrowdNetMPVPE108.5Unverified
10SMPLifyPA-MPJPE106.8Unverified
#ModelMetricClaimedVerifiedStatus
1VNect (Augm.)MPJPE124.7Unverified
2HMRMPJPE124.2Unverified
3Single-Shot Multi-PersonMPJPE122.2Unverified
4MehtaMPJPE117.6Unverified
5PONetMPJPE115Unverified
6Pose Consensus (monocular)MPJPE112.1Unverified
7GeoRep (fully-supervised)MPJPE110.8Unverified
8XFormer (HRNet)MPJPE109.8Unverified
9EpipolarPose (fully-supervised)MPJPE108.99Unverified
10SPINMPJPE105.2Unverified