SOTAVerified

Human Mesh Recovery

Estimate 3D body mesh from images

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 51–75 of 109 papers

TitleStatusHype
Multimodal Active Measurement for Human Mesh Recovery in Close ProximityCode0
Multi-RoI Human Mesh Recovery with Camera Consistency and Contrastive LossesCode0
Optimizing Local-Global Dependencies for Accurate 3D Human Pose EstimationCode0
Utilizing Uncertainty in 2D Pose Detectors for Probabilistic 3D Human Mesh RecoveryCode0
Full-Body Awareness from Partial Observations—0
Joint Optimization for 4D Human-Scene Reconstruction in the Wild—0
Fish2Mesh Transformer: 3D Human Mesh Recovery from Egocentric Vision—0
Towards Robust RGB-D Human Mesh Recovery—0
Everybody Is Unique: Towards Unbiased Human Mesh Recovery—0
Learning Dense UV Completion for Human Mesh Recovery—0
Learning Human Mesh Recovery in 3D Scenes—0
Learning Local Recurrent Models for Human Mesh Recovery—0
EgoGen: An Egocentric Synthetic Data Generator—0
Distribution and Depth-Aware Transformers for 3D Human Mesh Recovery—0
M3GYM: A Large-Scale Multimodal Multi-view Multi-person Pose Dataset for Fitness Activity Understanding in Real-world Settings—0
MEGA: Masked Generative Autoencoder for Human Mesh Recovery—0
MetricHMR: Metric Human Mesh Recovery from Monocular Images—0
Uncertainty-Aware Human Mesh Recovery From Video by Learning Part-Based 3D Dynamics—0
Distribution-Aligned Diffusion for Human Mesh Recovery—0
DiSRT-In-Bed: Diffusion-Based Sim-to-Real Transfer Framework for In-Bed Human Mesh Recovery—0
DiffSurf: A Transformer-based Diffusion Model for Generating and Reconstructing 3D Surfaces in Pose—0
Multi-Human Mesh Recovery with Transformers—0
Appearance Consensus Driven Self-Supervised Human Mesh Recovery—0
3D Human Scan With A Moving Event Camera—0
Multi-view Human Body Mesh Translator—0
Show:102550
← PrevPage 3 of 5Next →

Benchmark Results

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