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
KTPFormer: Kinematics and Trajectory Prior Knowledge-Enhanced Transformer for 3D Human Pose EstimationCode2
PoseTriplet: Co-evolving 3D Human Pose Estimation, Imitation, and Hallucination under Self-supervisionCode2
Hulk: A Universal Knowledge Translator for Human-Centric TasksCode2
Hourglass Tokenizer for Efficient Transformer-Based 3D Human Pose EstimationCode2
HybrIK: A Hybrid Analytical-Neural Inverse Kinematics Solution for 3D Human Pose and Shape EstimationCode2
FinePOSE: Fine-Grained Prompt-Driven 3D Human Pose Estimation via Diffusion ModelsCode2
ETCH: Generalizing Body Fitting to Clothed Humans via Equivariant TightnessCode2
FrankMocap: A Monocular 3D Whole-Body Pose Estimation System via Regression and IntegrationCode2
DensePose From WiFiCode2
AthletePose3D: A Benchmark Dataset for 3D Human Pose Estimation and Kinematic Validation in Athletic MovementsCode2
A Survey on 3D Egocentric Human Pose EstimationCode2
Deep learning for 3D human pose estimation and mesh recovery: A surveyCode2
Human-Art: A Versatile Human-Centric Dataset Bridging Natural and Artificial ScenesCode2
MogaNet: Multi-order Gated Aggregation NetworkCode2
H3WB: Human3.6M 3D WholeBody Dataset and BenchmarkCode2
Learning 3D Human Pose Estimation from Dozens of Datasets using a Geometry-Aware Autoencoder to Bridge Between Skeleton FormatsCode2
MixSTE: Seq2seq Mixed Spatio-Temporal Encoder for 3D Human Pose Estimation in VideoCode2
CrossFormer: Cross Spatio-Temporal Transformer for 3D Human Pose EstimationCode1
PyMAF: 3D Human Pose and Shape Regression with Pyramidal Mesh Alignment Feedback LoopCode1
Cyclic Test-Time Adaptation on Monocular Video for 3D Human Mesh ReconstructionCode1
Context Modeling in 3D Human Pose Estimation: A Unified PerspectiveCode1
3D Human Motion Estimation via Motion Compression and RefinementCode1
Cross-Attention of Disentangled Modalities for 3D Human Mesh Recovery with TransformersCode1
D&D: Learning Human Dynamics from Dynamic CameraCode1
Combining Implicit Function Learning and Parametric Models for 3D Human ReconstructionCode1
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