3D Human Pose Estimation
305 papers with code • 25 benchmarks • 46 datasets
3D Human Pose Estimation is a computer vision task that involves estimating the 3D positions and orientations of body joints and bones from 2D images or videos. The goal is to reconstruct the 3D pose of a person in real-time, which can be used in a variety of applications, such as virtual reality, human-computer interaction, and motion analysis.
Benchmarks
These leaderboards are used to track progress in 3D Human Pose Estimation
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
Libraries
Use these libraries to find 3D Human Pose Estimation models and implementationsDatasets
Human3.6M
Waymo Open Dataset
3DPW
AMASS
MPI-INF-3DHP
DensePose
LSP
Panoptic
AGORA
TotalCapture
Subtasks
Latest papers with no code
UPose3D: Uncertainty-Aware 3D Human Pose Estimation with Cross-View and Temporal Cues
At the core of our method, a pose compiler module refines predictions from a 2D keypoints estimator that operates on a single image by leveraging temporal and cross-view information.
EgoPoseFormer: A Simple Baseline for Egocentric 3D Human Pose Estimation
We also show that our method can be seamlessly extended to monocular settings, which achieves state-of-the-art performance on the SceneEgo dataset, improving MPJPE by 25. 5mm (21% improvement) compared to the best existing method with only 60. 7% model parameters and 36. 4% FLOPs.
Exploring 3D Human Pose Estimation and Forecasting from the Robot's Perspective: The HARPER Dataset
The scenario underlying HARPER includes 15 actions, of which 10 involve physical contact between the robot and users.
PostoMETRO: Pose Token Enhanced Mesh Transformer for Robust 3D Human Mesh Recovery
With the recent advancements in single-image-based human mesh recovery, there is a growing interest in enhancing its performance in certain extreme scenarios, such as occlusion, while maintaining overall model accuracy.
Self-learning Canonical Space for Multi-view 3D Human Pose Estimation
To facilitate the aggregation of the intra- and inter-view, we define a canonical parameter space, depicted by per-view camera pose and human pose and shape parameters ($\theta$ and $\beta$) of SMPL model, and propose a two-stage learning procedure.
NToP: NeRF-Powered Large-scale Dataset Generation for 2D and 3D Human Pose Estimation in Top-View Fisheye Images
Through this pipeline, we create a novel dataset NToP570K (NeRF-powered Top-view human Pose dataset for fisheye cameras with over 570 thousand images), and conduct an extensive evaluation of its efficacy in enhancing neural networks for 2D and 3D top-view human pose estimation.
Occlusion Resilient 3D Human Pose Estimation
Occlusions remain one of the key challenges in 3D body pose estimation from single-camera video sequences.
Uncertainty-Aware Testing-Time Optimization for 3D Human Pose Estimation
We observe that previous optimization-based methods commonly rely on projection constraint, which only ensures alignment in 2D space, potentially leading to the overfitting problem.
Multi-Person 3D Pose Estimation from Multi-View Uncalibrated Depth Cameras
In order to evaluate our proposed pipeline, we collect three video sets of RGBD videos recorded from multiple sparse-view depth cameras and ground truth 3D poses are manually annotated.
D3PRefiner: A Diffusion-based Denoise Method for 3D Human Pose Refinement
Additionally, we leverage the architecture of current diffusion models to convert the distribution of noisy 3D poses into ground truth 3D poses.
