3D_multiview_reg
3D_multiview_reg copied to clipboard
color information in the descriptor
Currently, only the coord info are used for training to generate the descriptor, did you also try to include the color information, i think it should be helpful in some difficult case also
We did not as our purpose was to investigate how far we could go by just using geometry. Color can indeed improve things. I would recommend to use a robust color space rather than plain RGB, such as sRGB or HSV/Lab.