HyperAIHyperAI
HomeConsoleDocsNewsPapersTutorialsDatasetsWikiSOTALLM ModelsGPU LeaderboardEvents
Search
About
HyperAIHyperAI

Command Palette

Search for a command to run...

Weakly Supervised 3D Human Pose Estimation On

Metrics

Average MPJPE (mm)

Results

Performance results of various models on this benchmark

Paper TitleRepository
Rhodin et al.131.7Unsupervised Geometry-Aware Representation for 3D Human Pose Estimation
Pavlakos et al.118.4Harvesting Multiple Views for Marker-less 3D Human Pose Annotations-
Pavlakos et al.110.7TexturePose: Supervising Human Mesh Estimation with Texture Consistency
HW-HuP104.1Heuristic Weakly Supervised 3D Human Pose Estimation
self-supervised mocap98.4Self-supervised Learning of Motion Capture
RepNet89.9RepNet: Weakly Supervised Training of an Adversarial Reprojection Network for 3D Human Pose Estimation
Li et al.88.8On Boosting Single-Frame 3D Human Pose Estimation via Monocular Videos-
Tome et al.88.4Lifting from the Deep: Convolutional 3D Pose Estimation from a Single Image
Wang et al.83.0Distill Knowledge from NRSfM for Weakly Supervised 3D Pose Learning-
EpipolarPose (self-supervised)76.6Self-Supervised Learning of 3D Human Pose using Multi-view Geometry
CanonPose74.3CanonPose: Self-Supervised Monocular 3D Human Pose Estimation in the Wild
GeoRep67.4Weakly-Supervised 3D Human Pose Learning via Multi-view Images in the Wild-
EpipolarPose (S1)65.35Self-Supervised Learning of 3D Human Pose using Multi-view Geometry
Triangulation64.7On Triangulation as a Form of Self-Supervision for 3D Human Pose Estimation-
Pavllo et al.64.73D human pose estimation in video with temporal convolutions and semi-supervised training
TriPose62.9TriPose: A Weakly-Supervised 3D Human Pose Estimation via Triangulation from Video-
Li et al.62.9Cascaded deep monocular 3D human pose estimation with evolutionary training data
2D-3D Lifting self-supervised62.0Self-Supervised 3D Human Pose Estimation with Multiple-View Geometry
EpipolarPose (SS + RU)60.56Self-Supervised Learning of 3D Human Pose using Multi-view Geometry
GeoRep (semi-supervised)59.7Weakly-Supervised 3D Human Pose Learning via Multi-view Images in the Wild-
0 of 33 row(s) selected.
Weakly Supervised 3D Human Pose Estimation On | SOTA | HyperAI