vLAR-group/DM-NeRF

Preprocessing of ScanNet scenes

liqi0126 opened this issue · 2 comments

Hi,

can you show how to preprocess scannet scenes for training? I tried to run preprocess.py first and then split.py. It gave me train and test split, but when running train_scannet.py it says ins_rgb.hdf5 is missing. How should i get this hdf5 file?

Thank you!

@liqi0126 Hi,

Thx for your attention. For the scannet processing, you can follow the official script of semantic instance generation method. By the way, .hdf5 file just includes the rgbs randomly generated by myself, you can generate it by yourself and put it to corresponding folder.

Could you elaborate what does this hdf5 do and its structure? Or maybe you can share with me your randomly generated hdf5?