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 2650 of 665 papers

TitleStatusHype
NIKI: Neural Inverse Kinematics with Invertible Neural Networks for 3D Human Pose and Shape EstimationCode2
PoseFormerV2: Exploring Frequency Domain for Efficient and Robust 3D Human Pose EstimationCode2
One-Stage 3D Whole-Body Mesh Recovery with Component Aware TransformerCode2
3D Human Mesh Estimation from Virtual MarkersCode2
Human-Art: A Versatile Human-Centric Dataset Bridging Natural and Artificial ScenesCode2
DensePose From WiFiCode2
Learning 3D Human Pose Estimation from Dozens of Datasets using a Geometry-Aware Autoencoder to Bridge Between Skeleton FormatsCode2
H3WB: Human3.6M 3D WholeBody Dataset and BenchmarkCode2
MogaNet: Multi-order Gated Aggregation NetworkCode2
PyMAF-X: Towards Well-aligned Full-body Model Regression from Monocular ImagesCode2
Not All Tokens Are Equal: Human-centric Visual Analysis via Token Clustering TransformerCode2
PoseTriplet: Co-evolving 3D Human Pose Estimation, Imitation, and Hallucination under Self-supervisionCode2
MixSTE: Seq2seq Mixed Spatio-Temporal Encoder for 3D Human Pose Estimation in VideoCode2
ICON: Implicit Clothed humans Obtained from NormalsCode2
FrankMocap: A Monocular 3D Whole-Body Pose Estimation System via Regression and IntegrationCode2
HybrIK: A Hybrid Analytical-Neural Inverse Kinematics Solution for 3D Human Pose and Shape EstimationCode2
Monocular, One-stage, Regression of Multiple 3D PeopleCode2
PoseBench3D: A Cross-Dataset Analysis Framework for 3D Human Pose EstimationCode1
Towards Robust and Realistic Human Pose Estimation via WiFi SignalsCode1
Pre-training a Density-Aware Pose Transformer for Robust LiDAR-based 3D Human Pose EstimationCode1
BLAPose: Enhancing 3D Human Pose Estimation with Bone Length AdjustmentCode1
ARTS: Semi-Analytical Regressor using Disentangled Skeletal Representations for Human Mesh Recovery from VideosCode1
Leveraging Anthropometric Measurements to Improve Human Mesh Estimation and Ensure Consistent Body ShapesCode1
SPiKE: 3D Human Pose from Point Cloud SequencesCode1
PAFUSE: Part-based Diffusion for 3D Whole-Body Pose EstimationCode1
Show:102550
← PrevPage 2 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