SQN

SQN copied to clipboard

Hi @QingyongHu！ Thanks for your work! I noticed that you have adopted a new random sparse annotation approach when working with the KITTI dataset. But I think that approach will...

lex940728

Hello, Thank you your work. I could not see the code for the ScanNet dataset. Is it possible for you to share the code for ScanNet as well. Also, can...

mertkiray

How to get class weights with weak labels?

5

Hi @QingyongHu, thanks for your awesome work! You use class weighted loss while training, where class weights are calculate from full annotations, as shown in the following figure. Have you...

Anna0509

当我修改了SQN中main_S3DIS.py代码后处理自己的数据集，会报`段错误（核心已转储）`错误。但是对RandLA中修改main_S3DIS.py后处理自己的数据集没有报错。这是什么原因造成的呢？谢谢 请问下可以公布下处理Sensat_Urban数据集代码吗？

volare1996

Hello, Thanks for your nice work! I would like to ask about table 9 in the appendix You report 5299M raw point cloud in Semantic KITTI, but in the Semantic...

anhquancao

Annotation cost for 1‰ label. For a dataset with dense points

1

Thanks for your awesome work! I'd like to ask about the annotation cost of your work For example, one of the rooms in S3DIS has over 9,000,000 points. Does that...

Cheater-Hater

looking forward to pytorch version

1

cuge1995

Where is the code?

1

The repository only contains README and LICENSE files. Where can we find the code?

ceteke

Hello, Thank you your work. I could not see the code for the ScanNet dataset. Is it possible for you to share the code for ScanNet as well？

xuxiaoxxxx

The test set label for the dataset SensatUrban

1

您好，胡博士，想咨询下就是您论文SQN使用的数据集SensatUrban的标签可以公开么？还是我们自己运行后提交到您之前发布的网页，让系统在线出结果啊？

SC-shendazt