SOTAVerified

3D Absolute Human Pose Estimation

This task aims to solve absolute (camera-centric not root-relative) 3D human pose estimation.

( Image credit: RootNet )

Papers

Showing 110 of 13 papers

TitleStatusHype
Understanding Diffusion Models: A Unified Perspective0
XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory ModelCode3
The Best of Both Worlds: Combining Model-based and Nonparametric Approaches for 3D Human Body Estimation0
Out-of-Domain Human Mesh Reconstruction via Dynamic Bilevel Online AdaptationCode1
Encoder-decoder with Multi-level Attention for 3D Human Shape and Pose EstimationCode1
Graph and Temporal Convolutional Networks for 3D Multi-person Pose Estimation in Monocular VideosCode1
End-to-End Human Pose and Mesh Reconstruction with TransformersCode1
MeTRAbs: Metric-Scale Truncation-Robust Heatmaps for Absolute 3D Human Pose EstimationCode1
Fusing Wearable IMUs with Multi-View Images for Human Pose Estimation: A Geometric ApproachCode1
Camera Distance-aware Top-down Approach for 3D Multi-person Pose Estimation from a Single RGB ImageCode0
Show:102550
← PrevPage 1 of 2Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1RootNetMRPE120Unverified
2GnTCNMRPE88.1Unverified
3Pose GrammarAverage MPJPE (mm)60.4Unverified
4MBNAPA-MPJPE38.4Unverified