search

autonomousvision / occupancy_networks

This repository contains the code for the paper "Occupancy Networks - Learning 3D Reconstruction in Function Space"
https://avg.is.tuebingen.mpg.de/publications/occupancy-networks
MIT License
1.49k stars 291 forks source link

has anyone trained on all category? #76

Open hua-wu-que opened 4 years ago

hua-wu-que commented 4 years ago

Hi!

I wonder if anyone has experience train one model on all category instead of one model for each category? What are the performance be like? Thank you!

Wuziyi616 commented 4 years ago

Hi! Actually some of the pre-trained weights provided in this repo is indeed trained on all 13 classes of ShapeNet. For example the 'configs/img/onet_pretrained.yaml', 'configs/pointcloud/onet_pretrained.yaml' and 'configs/voxels/onet_pretrained.yaml'. I have tested one of them (pointcloud pre-trained weight) and it generalizes well across categories.

Hope this can help you!

albertotono commented 3 years ago

Hi @Wuziyi616 and @hua-wu-que , is it possible to extrapolate from the demo or the trained model the category for inference? I can only see the mesh as output, where can I find the category?