Open yjcaimeow opened 2 years ago
create_cluster_masks.py has the logic we use to partition the pixels to per-cell training datasets. The basic idea is to sample points along the ray and see if any of those points fall within a given cell. If any sample does, we include it in the training set for that cell.
Dear @jaharkes @hturki @therealsatya @teiszler
Thanks the great work! But I have some understing. How to assign a pixel to certain 3D cell? Using the depth of the pixel? There are many sample locations on a ray of a pixel. How to process the sample locations?
Best, Yingjie CAI