SOTAVerified

Human Mesh Recovery

Estimate 3D body mesh from images

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 51–60 of 109 papers

TitleStatusHype
M3GYM: A Large-Scale Multimodal Multi-view Multi-person Pose Dataset for Fitness Activity Understanding in Real-world Settings—0
Optimizing Local-Global Dependencies for Accurate 3D Human Pose EstimationCode0
GenHMR: Generative Human Mesh Recovery—0
CondiMen: Conditional Multi-Person Mesh Recovery—0
BLADE: Single-view Body Mesh Learning through Accurate Depth Estimation—0
HeatFormer: A Neural Optimizer for Multiview Human Mesh Recovery—0
Continuous-Time Human Motion Field from Events—0
Utilizing Uncertainty in 2D Pose Detectors for Probabilistic 3D Human Mesh RecoveryCode0
DeforHMR: Vision Transformer with Deformable Cross-Attention for 3D Human Mesh Recovery—0
DiffSurf: A Transformer-based Diffusion Model for Generating and Reconstructing 3D Surfaces in Pose—0
Show:102550
← PrevPage 6 of 11Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1BEDLAM-CLIFFPVE-All94.6—Unverified
2BEDLAM-CLIFF+PVE-All87.6—Unverified
3Multi-HMRPVE-All76.8—Unverified