train AtlasNet on own dataset
qiminchen opened this issue · comments
Hi,
Is it possible to train the AtlasNet on our own dataset? If so, what data should I generate if I have 2D RGB images and corresponding 3D objects? And I only want to synthesize a mesh from a single image. Thanks
Hi @qiminchen. Happy new year !
You have to replace atlasnet dataloader AtlasNet/dataset/dataset_shapenet.py
with your own dataloader. It should output a python dictionary with the entry keys image
, points
, pointcloud_path
, image_path
, name
, and category
.
Cheers,
Thibault