Weakly-supervised 3D Human Pose Estimation
18 papers with code • 2 benchmarks • 2 datasets
This task targets at 3D Human Pose Estimation with fewer 3D annotation.
Benchmarks
These leaderboards are used to track progress in Weakly-supervised 3D Human Pose Estimation
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
Libraries
Use these libraries to find Weakly-supervised 3D Human Pose Estimation models and implementations
Human3.6M
MPI-INF-3DHP
Most implemented papers
CanonPose: Self-Supervised Monocular 3D Human Pose Estimation in the Wild
bastianwandt/CanonPose
•
•
CVPR 2021
Human pose estimation from single images is a challenging problem in computer vision that requires large amounts of labeled training data to be solved accurately.
PoseAug: A Differentiable Pose Augmentation Framework for 3D Human Pose Estimation
jfzhang95/PoseAug
•
•
CVPR 2021
To address this problem, we present PoseAug, a new auto-augmentation framework that learns to augment the available training poses towards a greater diversity and thus improve generalization of the trained 2D-to-3D pose estimator.
MetaPose: Fast 3D Pose from Multiple Views without 3D Supervision
google-research/google-research
•
•
CVPR 2022
In the era of deep learning, human pose estimation from multiple cameras with unknown calibration has received little attention to date.
Self-Supervised 3D Human Pose Estimation with Multiple-View Geometry
vru2020/Pose_3D
•
•
We present a self-supervised learning algorithm for 3D human pose estimation of a single person based on a multiple-view camera system and 2D body pose estimates for each view.
Unsupervised 3D Pose Estimation for Hierarchical Dance Video Recognition
garfield-kh/posetriplet
•
•
ICCV 2021
Dance experts often view dance as a hierarchy of information, spanning low-level (raw images, image sequences), mid-levels (human poses and bodypart movements), and high-level (dance genre).
AdaptPose: Cross-Dataset Adaptation for 3D Human Pose Estimation by Learnable Motion Generation
mgholamikn/AdaptPose
•
•
CVPR 2022
To this end, we propose AdaptPose, an end-to-end framework that generates synthetic 3D human motions from a source dataset and uses them to fine-tune a 3D pose estimator.
Automatic Labeling of Parkinson’s Disease Gait Videos with Weak Supervision
mgholamikn/PD_Gait_labeling
•
•
Medical Image Analysis 2023
The method obtained state-of-the-art results on the Human3. 6M dataset.
A Dual-Augmentor Framework for Domain Generalization in 3D Human Pose Estimation
Furthermore, the pose estimator's optimization is not exposed to domain shifts, limiting its overall generalization ability.
