SOTAVerified

3D human pose and shape estimation

Estimate 3D human pose and shape (e.g. SMPL) from images

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 11–20 of 50 papers

TitleStatusHype
AnthroNet: Conditional Generation of Humans via AnthropometricsCode1
PointHPS: Cascaded 3D Human Pose and Shape Estimation from Point Clouds—0
NIKI: Neural Inverse Kinematics with Invertible Neural Networks for 3D Human Pose and Shape EstimationCode2
HuManiFlow: Ancestor-Conditioned Normalising Flows on SO(3) Manifolds for Human Pose and Shape Distribution EstimationCode1
Global-to-Local Modeling for Video-based 3D Human Pose and Shape EstimationCode1
PSVT: End-to-End Multi-person 3D Pose and Shape Estimation with Progressive Video Transformers—0
Rethinking Self-Supervised Visual Representation Learning in Pre-training for 3D Human Pose and Shape Estimation—0
Capturing the motion of every joint: 3D human pose and shape estimation with independent tokensCode1
3D Human Pose and Shape Estimation via HybrIK-TransformerCode1
IKOL: Inverse kinematics optimization layer for 3D human pose and shape estimation via Gauss-Newton differentiationCode1
Show:102550
← PrevPage 2 of 5Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1SemanticsTTA (HMR2.0)Average MPJPE (mm)104.6—Unverified
2MEEVAverage MPJPE (mm)82.3—Unverified