ShapeFormer
ShapeFormer copied to clipboard
Official repository for the ShapeFormer Project
Thanks for sharing the source code. Just one thing to clarify, I want to ask whether the ShapeFormer model is trained separately on different datasets in the Shape completion results...
Thank you for a great work I want to know how many points are sampled from the completed meshes when calculating CD, F1, FPD in table 1 and table 3...
how can i solve this problem? python -m shapeformer.trainer --opts configs/demo/demo_vqdif.yaml --gpu 0 --mode "run" **** INFO **** Choosing GPUS: [0] **** INFO **** Resetting GPUS ids to: [0] ****...
Thanks for your excellent work. I have a question after reading your paper. In the paper, does a partial correspond to a GT for supervision? If so, why can multi-modal...
Thank for you great work, i want to ask 1、did you multiple any scale of your CD ? 2、In figure.9 left, i think here CD should be equal to table....
Hi, I am not able to set up the conda environment. It keeps on reading the environment file for more than 3-4 hours. are there any additional requirements ?
Hello! I'm curious to try ShapeFormer on my own .ply mesh. I have converted it into a numpy array, however I see that the original demo data has 2 .npy...
Thank you very much for your great work! I am trying to use the full dataset of `IMnet` and `HSP` to train ShapeFormer. I discovered the `make_imnet_dataset` function in `shapeformer/data/imnet_datasets/imnet_datasets.py`...
Thank you for your excellent work! I was hoping to use the metric mentioned in your paper, but I'm having trouble locating any metric functions besides chamfer distance in the...