Chenfeng Xu

Hi, thanks for your kind pinpoint. I make a mistake here, the right one should be range: 12.12 and z: -1.04, I believe the right one will lead to a...

Hi, thanks for your inform. It seems that some dependencies have conflicts now. I have updated a new requirements file and some codes, and tested on a new machine. Everything...

Hi, we train our model on eight Titan RTX (24G) GPUs. For SSGV321, the batch size is 2 for each GPU and it costs about 16G on each one. For...

I briefly write the pseudo code you may refer to. with torch.no_grad(): end = time.time() meanr = 0. stdr = 0. meanx = 0. meany = 0. meanz = 0....

Good observation! We didn't notice this before. I think it is the dataset that doesn't provide labels on these kinds of scenes, because they usually represents very far points where...

Thanks, we will release the pretrained model after 8/1/2021 due to some rights checking issues. BTW directly training from scratch would be fast if you were urgent to use. Feel...

Thanks for indicating my missing data-preprocess code. I have updated it in readme now. You can go to data/s3dis folder and run python prepare_data.py to get the preprocessed s3dis data....

Yes, you are right to run this for evaluation.

I suppose you use our default setting vote number = 1 in the config file. Sorry for confusing you. As illustrated in the paper, we vote 10 times during the...

Also thank you for your feedback to help us improve the quality of this repo :). Also, feel free to contact me if you have other issues.