Meida Chen

> Or, if not using WMSC as validation, only as testing, 3 or 5 times average is also OK. In this case, I think cross-validation would be a better option.

Hi @volare1996 , Which two sets of data are you using?

Hi @ageorgiev97 , Yes, and yes. We are still preparing the models, are you interested in the semantic segmentation or the instance segmentation?

Hi @ageorgiev97 , Yes, and yes. We are still preparing the models, are you interested in the semantic segmentation or the instance segmentation?

We are still preparing the data generation scripts and instructions since the scripts were not currently all connected smoothly and a lot more work needed to be done to make...

We only provided the minimum functions (training and testing) of KpConv for our data sets. For complete functionalities of KpConv, please refer to the official KpConv release.

Hi @thangvubk , Really appreciate your feedback and implementing SoftGroup for STPLS3D!!! Regarding the performance, we have recently found an issue in the evaluation script we provided in HAIS as...

Wow!! really nice work!! Could you please share the result table with me? and I will make the update here.

Great! Thank you!

SoftGroup result was uploaded to this repo with all related information. Thanks again for the implementation, and I hope to see you in the Urban3D workshop soon!