Hello! I have a question regarding the training of Point-BERT. In your paper, you claim what follows:
As the original implementation of ULIP-2 only supports point clouds with spatial coordinates (xyz), we re-train Point-BERT with color information (xyzrgb), following the same procedure outlined in the ULIP-2 paper. For training Point-BERT, we employ ViT-L/14 from OpenCLIP [20] and use point clouds from the Cap3D [29] dataset...
I am wondering if you trained Point-BERT from scratch, by following ULIP-2 pipeline (aligning 3D features with 2D and text features) or finetuned it starting from a Point-BERT model trained on the reconstruction task, as the original Point-BERT paper suggests.
Hello! I have a question regarding the training of Point-BERT. In your paper, you claim what follows:
I am wondering if you trained Point-BERT from scratch, by following ULIP-2 pipeline (aligning 3D features with 2D and text features) or finetuned it starting from a Point-BERT model trained on the reconstruction task, as the original Point-BERT paper suggests.
Thanks in advance, Andrea