Monocular 3D Human Pose Estimation
65 papers with code • 1 benchmarks • 5 datasets
This task targets at 3D human pose estimation with a single RGB camera.
Benchmarks
These leaderboards are used to track progress in Monocular 3D Human Pose Estimation
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
Libraries
Use these libraries to find Monocular 3D Human Pose Estimation models and implementations
Human3.6M
AGORA
3DOH50K
HBW
H3WB
Most implemented papers
3D Human Pose Estimation with Spatial and Temporal Transformers
zczcwh/PoseFormer
•
•
ICCV 2021
Transformer architectures have become the model of choice in natural language processing and are now being introduced into computer vision tasks such as image classification, object detection, and semantic segmentation.
Unite the People: Closing the Loop Between 3D and 2D Human Representations
MandyMo/pytorch_HMR
•
•
CVPR 2017
With a comprehensive set of experiments, we show how this data can be used to train discriminative models that produce results with an unprecedented level of detail: our models predict 31 segments and 91 landmark locations on the body.
Neural Body Fitting: Unifying Deep Learning and Model-Based Human Pose and Shape Estimation
mohomran/neural_body_fitting
•
•
Direct prediction of 3D body pose and shape remains a challenge even for highly parameterized deep learning models.
Generating Multiple Hypotheses for 3D Human Pose Estimation with Mixture Density Network
chaneyddtt/Generating-Multiple-Hypotheses-for-3D-Human-Pose-Estimation-with-Mixture-Density-Network
•
•
CVPR 2019
We argue that 3D human pose estimation from a monocular input is an inverse problem where multiple feasible solutions can exist.
Convolutional Mesh Regression for Single-Image Human Shape Reconstruction
Image-based features are attached to the mesh vertices and the Graph-CNN is responsible to process them on the mesh structure, while the regression target for each vertex is its 3D location.
Heuristic Weakly Supervised 3D Human Pose Estimation
However, recent models depend on supervised training with 3D pose ground truth data or known pose priors for their target domains.
ICON: Implicit Clothed humans Obtained from Normals
First, ICON infers detailed clothed-human normals (front/back) conditioned on the SMPL(-X) normals.
Capturing and Inferring Dense Full-Body Human-Scene Contact
We capture a new dataset called RICH for "Real scenes, Interaction, Contact and Humans."
DiffPose: Toward More Reliable 3D Pose Estimation
GONGJIA0208/Diffpose
•
•
CVPR 2023
Monocular 3D human pose estimation is quite challenging due to the inherent ambiguity and occlusion, which often lead to high uncertainty and indeterminacy.
Sparseness Meets Deepness: 3D Human Pose Estimation from Monocular Video
chuxiaoselena/SparsenessMeetsDeepness
•
•
CVPR 2016
Here, two cases are considered: (i) the image locations of the human joints are provided and (ii) the image locations of joints are unknown.
