Giters

yuxumin / PoinTr

[ICCV 2021 Oral] PoinTr: Diverse Point Cloud Completion with Geometry-Aware Transformers

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

How the foreground region is determined for downstream object detection tasks

HenryHoou opened this issue · comments

commented

Thanks for your excellent work！
You mentioned in TPAMI paper that predicting the complete shape of objects in the foreground category goes in parallel with categorizing and determining the box, so are the details of this step going to isolate the foreground category and proceed to completion or are you going to directly input the larger region?What is your method for determining the foreground？