HyperAIHyperAI

Weakly Supervised 3D Human Pose Estimation On

Métriques

Average MPJPE (mm)

Résultats

Résultats de performance de divers modèles sur ce benchmark

Nom du modèle
Average MPJPE (mm)
Paper TitleRepository
EpipolarPose (SS + RU)60.56Self-Supervised Learning of 3D Human Pose using Multi-view Geometry-
AdaptPose42.5AdaptPose: Cross-Dataset Adaptation for 3D Human Pose Estimation by Learnable Motion Generation-
RepNet89.9RepNet: Weakly Supervised Training of an Adversarial Reprojection Network for 3D Human Pose Estimation-
DAF-DG50.3A Dual-Augmentor Framework for Domain Generalization in 3D Human Pose Estimation-
GeoRep67.4Weakly-Supervised 3D Human Pose Learning via Multi-view Images in the Wild-
PGNIS50.8Self-Supervised 3D Human Pose Estimation via Part Guided Novel Image Synthesis-
EpipolarPose (self-supervised)76.6Self-Supervised Learning of 3D Human Pose using Multi-view Geometry-
Non-Local Latent Relation Distillation57.6Non-Local Latent Relation Distillation for Self-Adaptive 3D Human Pose Estimation-
Kocabas et al.-Self-Supervised Learning of 3D Human Pose using Multi-view Geometry-
VideoPose3D (T=243)-3D human pose estimation in video with temporal convolutions and semi-supervised training-
Pavlakos et al.110.7TexturePose: Supervising Human Mesh Estimation with Texture Consistency-
2D-3D Lifting self-supervised62.0Self-Supervised 3D Human Pose Estimation with Multiple-View Geometry-
self-supervised mocap98.4Self-supervised Learning of Motion Capture-
CanonPose74.3CanonPose: Self-Supervised Monocular 3D Human Pose Estimation in the Wild-
Li et al.88.8On Boosting Single-Frame 3D Human Pose Estimation via Monocular Videos-
HDVR47.3Unsupervised 3D Pose Estimation for Hierarchical Dance Video Recognition-
Uncertainty-Aware Adaptation59.4Uncertainty-Aware Adaptation for Self-Supervised 3D Human Pose Estimation-
EpipolarPose (S1)65.35Self-Supervised Learning of 3D Human Pose using Multi-view Geometry-
Tome et al.88.4Lifting from the Deep: Convolutional 3D Pose Estimation from a Single Image-
Triangulation64.7On Triangulation as a Form of Self-Supervision for 3D Human Pose Estimation-
0 of 33 row(s) selected.
Weakly Supervised 3D Human Pose Estimation On | SOTA | HyperAI