You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
We will soon have several different methods for inverting from GelSight RGB to gradients. These different methods have different initializations and invocations, and so it would be nice to have them encapsulated in classes where the constructors would handle initialization (and paramaterization, if there is any) and the class would have a method convertRGBToGradients for the inversion.
Inversion methods we have so far:
convolution filter applied to BGSub'd image
spatially-varying lookup table applied throughout the RGB image
octree-based XY->RGB inversion
lookup bin RGB->XY mapping
EDIT: added last two inversion methods
The text was updated successfully, but these errors were encountered:
We will soon have several different methods for inverting from GelSight RGB to gradients. These different methods have different initializations and invocations, and so it would be nice to have them encapsulated in classes where the constructors would handle initialization (and paramaterization, if there is any) and the class would have a method convertRGBToGradients for the inversion.
Inversion methods we have so far:
EDIT: added last two inversion methods
The text was updated successfully, but these errors were encountered: