Datasets with vastly varying edge counts

ranahanocka / MeshCNN

Convolutional Neural Network for 3D meshes in PyTorch

MIT License

1.56k stars 314 forks source link

Datasets with vastly varying edge counts #23

Closed mrmoss closed 4 years ago

mrmoss commented 4 years ago

Some of the larger datasets out there (such as Shapenet and ABC) have edge counts ranging from 100's to 100000's.

Do you have any advice on selecting a pool_res and ncf for datasets with this sort of edge count variation? And/or any thoughts on the effect this would have on your research?

ranahanocka commented 4 years ago

Hi @mrmoss ,

I responded to a similar question in this issue. Basically, I suggest processing the data first. I just posted a very basic script to do this in blender here.