About Input?
ming-dream opened this issue · comments
How can I get the 2.5d input(the two npz)from a image?
@ming-dream see #5 . The processing steps and code are there.
Sorry,I still don't understand the step of changing an image in to two npzs. Is the image just a png? Could you show me an example,thanks in advance.
@ming-dream One depth image is processed to be only one "npz" file. The other "npz" file is the corresponding 3D groundtruth which is generated thru voxelization algorithm or the "binvox" tool.
I added a "Data_preprocess" folder in the gitHub repository, which showcases how to transfer a single depth image to a 256^3 voxel grid. Please check it out. https://github.com/Yang7879/3D-RecGAN-extended/tree/master/Data_preprocess