3D Hand Pose Estimation
64 papers with code • 5 benchmarks • 16 datasets
Image: Zimmerman et l
Benchmarks
These leaderboards are used to track progress in 3D Hand Pose Estimation
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
|||||
|
|||||
|
Libraries
Use these libraries to find 3D Hand Pose Estimation models and implementationsDatasets
FreiHAND
HO-3D
DexYCB
AGORA
InterHand2.6M
ExPose
3D Hand Pose
First-Person Hand Action Benchmark
EgoDexter
SynthHands
Most implemented papers
3D Hand Pose Estimation using Simulation and Partial-Supervision with a Shared Latent Space
masabdi/LSPS
•
•
British Machine Vision Conference 2018 2018
In this paper, we propose a novel method that seeks to predict the 3d position of the hand using both synthetic and partially-labeled real data.
MURAUER: Mapping Unlabeled Real Data for Label AUstERity
poier/murauer
•
•
In this work, we remove this requirement by learning to map from the features of real data to the features of synthetic data mainly using a large amount of synthetic and unlabeled real data.
Pixel-wise Regression: 3D Hand Pose Estimation via Spatial-form Representation and Differentiable Decoder
IcarusWizard/PixelwiseRegression
•
•
To use our method, we build a model, in which we design a particular SFR and its correlative DD which divided the 3D joint coordinates into two parts, plane coordinates and depth coordinates and use two modules named Plane Regression (PR) and Depth Regression (DR) to deal with them respectively.
Exploiting Spatial-Temporal Relationships for 3D Pose Estimation via Graph Convolutional Networks
vanoracai/Exploiting-Spatial-temporal-Relationships-for-3D-Pose-Estimation-via-Graph-Convolutional-Networks
•
•
ICCV 2019
Despite great progress in 3D pose estimation from single-view images or videos, it remains a challenging task due to the substantial depth ambiguity and severe self-occlusions.
HandAugment: A Simple Data Augmentation Method for Depth-Based 3D Hand Pose Estimation
wozhangzhaohui/HandAugment
•
•
Our method has two main parts: First, We propose a scheme of two-stage neural networks.
Epipolar Transformers
yihui-he/epipolar-transformers
•
•
CVPR 2020
The intuition is: given a 2D location p in the current view, we would like to first find its corresponding point p' in a neighboring view, and then combine the features at p' with the features at p, thus leading to a 3D-aware feature at p. Inspired by stereo matching, the epipolar transformer leverages epipolar constraints and feature matching to approximate the features at p'.
JGR-P2O: Joint Graph Reasoning based Pixel-to-Offset Prediction Network for 3D Hand Pose Estimation from a Single Depth Image
fanglinpu/JGR-P2O
•
•
ECCV 2020
The key ideas are two-fold: a) explicitly modeling the dependencies among joints and the relations between the pixels and the joints for better local feature representation learning; b) unifying the dense pixel-wise offset predictions and direct joint regression for end-to-end training.
AWR: Adaptive Weighting Regression for 3D Hand Pose Estimation
Elody-07/AWR-Adaptive-Weighting-Regression
•
•
In this paper, we propose an adaptive weighting regression (AWR) method to leverage the advantages of both detection-based and regression-based methods.
Body2Hands: Learning to Infer 3D Hands from Conversational Gesture Body Dynamics
facebookresearch/body2hands
•
•
CVPR 2021
We demonstrate the efficacy of our method on hand gesture synthesis from body motion input, and as a strong body prior for single-view image-based 3D hand pose estimation.
I2L-MeshNet: Image-to-Lixel Prediction Network for Accurate 3D Human Pose and Mesh Estimation from a Single RGB Image
mks0601/I2L-MeshNet_RELEASE
•
•
ECCV 2020
Most of the previous image-based 3D human pose and mesh estimation methods estimate parameters of the human mesh model from an input image.
