How to adapt PointCLIP for part-segmentation task

[amiltonwong]

Hi, @ZrrSkywalker ,

Thanks for releasing the package and also the guide on ZSL for 3D object classification. I'm concerned about whether it's possible to adapt the PointCLIP method for part-segmentation task, e.g. ShapeNet part dataset. If yes, could you elaborate on the steps for achieving it?

Thanks~

[ZrrSkywalker]

Thanks for your interest on our work.
We have conducted zero-shot part segmentation on ShapeNetPart dataset in PointCLIP V2 by back-projecting CLIP's prediction from multi-view images. We will soon release the code after reviewing. Thanks.