Meida Chen

Hi @hongzhiqiang67 , RandLA was implemented using our old data pipeline, basically, it used the data in txt format instead of the current ply format. I will later try to...

Were you able to run the official RandLA using your environment?

Sure, USC: 34.020178, -118.288826 WMSC: 33.444650, -118.481350 OCCC: 28.429107, -81.461848 RA: 33.874179, -118.073325

Thanks for your interest in our datasets. But sorry I don't have a good answer for the label merging between different blocks, since I didn't try to do it myself....

I'm only trying to provide information I got from other STPLS3D users here (we haven't had a chance to test it but hopefully it is helpful). Special thanks to @ywyue,...

Hi, I have not looked into this issue and assumed that it will be a single instance for each point. I'm wondering have you tested it using ScanNetV2 or S3DIS...

Hi @whuhxb , We were using the RTX3090 on a windows machine with CUDA 11.0 to test the RandLA. Since we didn't make any changes to RandLA itself, but only...

> Hi @meidachen For RandLA-Net, you only used the RealWorldData for training the network, not the Synthetic data for training the network, right? I used both, just like our paper...

> Hi @meidachen > > Thanks so much for the answering. I have one question, the provided .txt file data contain both the RealWorldData and the Synthetic data, right? And,...

> Hi @meidachen Thanks for you detailed answering. If I train RandLA-Net with the .ply format input, could I refer to the KPConv data_prepare_STPLS3D.py to prepare the ply format data?...