HandOccNet: Occlusion-Robust 3D Hand Mesh Estimation Network

Introduction

This repository is the offical Pytorch implementation of HandOccNet: Occlusion-Robust 3D Hand Mesh Estimation Network (CVPR 2022).

Usage

Input an image containing a hand (occluded or not occluded), as well as bounding box coordinates in the comma-separated format <xmin,ymin,image_width,image_height>. The model will then output the bounding-box annotated image as well as a 3D hand model.

Reference

@InProceedings{Park_2022_CVPR_HandOccNet,  
author = {Park, JoonKyu and Oh, Yeonguk and Moon, Gyeongsik and Choi, Hongsuk and Lee, Kyoung Mu},  
title = {HandOccNet: Occlusion-Robust 3D Hand Mesh Estimation Network},  
booktitle = {Conference on Computer Vision and Pattern Recognition (CVPR)},  
year = {2022}  
}  

Acknowledgements

For this project, we relied on research codes from: * I2L-MeshNet_RELEASE * Semi-Hand-Object * attention-module