zyc000
zyc000
@mutianxu Thanks for your update!
Yes, I think using SAM's everything function is a good choice for your requirement. What you can do is to change the masks generated by GLIP+SAM to SAM everything output....
Thanks for your interest! We just released the training codes. We will release the data engine codes as soon as posible.
Thanks! Since 2048 is very sparse, I think it can't be rendered very well. What's more, PartNet's raw meshes provided on the website don't have material so that only gray...
Yes, you need to render view images. We didn't use BlenderProc for rendering but I'm sure it works. For rendering and point cloud fusion, I pushed the codes to 'fuse_pointcloud'...
Thanks! 'img_sp' is generated by 'gen_sp.py', you can run that script to generate files in this folder.
Thanks! If you want to train few-shot results, you should follow GLIP fine-tune instruction and use GLIP/tools/finetune.py to fine-tune the GLIP model with pretrained model 'glip_large_model.pth'. You can find that...