namepllet / HandOccNet

Offical pytorch implementation of "HandOccNet: Occlusion-Robust 3D Hand Mesh Estimation Network", CVPR 2022.
158 stars 31 forks source link

How to get the bbox in practical applications #36

Open CaptainWuDaoKou opened 3 months ago

CaptainWuDaoKou commented 3 months ago

Thanks for your great work! I discovered that during both the training and the reasoning process of the demo, it is necessary to provide the bbox marking the position of the human hand. I'm curious about how this bbox is obtained in practical applications, considering that it is very difficult for conventional methods to predict the complete area of the human hand when the hand is occluded by the object. Thanks