3D Pose Estimation
131 papers with code • 6 benchmarks • 29 datasets
Benchmarks
These leaderboards are used to track progress in 3D Pose Estimation
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
Libraries
Use these libraries to find 3D Pose Estimation models and implementations
Human3.6M
LSP
HO-3D
Hypersim
MuCo-3DHP
ApolloCar3D
SVIRO
Unite the People
CarFusion
Latest papers
EventEgo3D: 3D Human Motion Capture from Egocentric Event Streams
In response to the existing limitations, this paper 1) introduces a new problem, i. e., 3D human motion capture from an egocentric monocular event camera with a fisheye lens, and 2) proposes the first approach to it called EventEgo3D (EE3D).
SelfPose3d: Self-Supervised Multi-Person Multi-View 3d Pose Estimation
Unlike current state-of-the-art fully-supervised methods, our approach does not require any 2d or 3d ground-truth poses and uses only the multi-view input images from a calibrated camera setup and 2d pseudo poses generated from an off-the-shelf 2d human pose estimator.
Platypose: Calibrated Zero-Shot Multi-Hypothesis 3D Human Motion Estimation
In this study we focus on the new task of multi-hypothesis motion estimation.
Attention-Propagation Network for Egocentric Heatmap to 3D Pose Lifting
tho-kn/egotap
•
•
We propose a novel heatmap-to-3D lifting method composed of the Grid ViT Encoder and the Propagation Network.
3D Pose Estimation of Two Interacting Hands from a Monocular Event Camera
3D hand tracking from a monocular video is a very challenging problem due to hand interactions, occlusions, left-right hand ambiguity, and fast motion.
Mask as Supervision: Leveraging Unified Mask Information for Unsupervised 3D Pose Estimation
Automatic estimation of 3D human pose from monocular RGB images is a challenging and unsolved problem in computer vision.
MoEmo Vision Transformer: Integrating Cross-Attention and Movement Vectors in 3D Pose Estimation for HRI Emotion Detection
Santa-Clara-Media-Lab/MoEmo_Vision_Transformer
•
•
In the current effort, we introduce 1) MoEmo (Motion to Emotion), a cross-attention vision transformer (ViT) for human emotion detection within robotics systems based on 3D human pose estimations across various contexts, and 2) a data set that offers full-body videos of human movement and corresponding emotion labels based on human gestures and environmental contexts.
DeepSimHO: Stable Pose Estimation for Hand-Object Interaction via Physics Simulation
rongakowang/deepsimho
•
•
NeurIPS 2023
Specifically, for an initial hand-object pose estimated by a base network, we forward it to a physics simulator to evaluate its stability.
FreeMan: Towards Benchmarking 3D Human Pose Estimation under Real-World Conditions
To facilitate the development of 3D pose estimation, we present FreeMan, the first large-scale, multi-view dataset collected under the real-world conditions.
Probabilistic Triangulation for Uncalibrated Multi-View 3D Human Pose Estimation
bymaths/probabilistic_triangulation
•
•
ICCV 2023
The key idea is to use a probability distribution to model the camera pose and iteratively update the distribution from 2D features instead of using camera pose.
