Use correlation as loss

[bkvie]

correlation(image1, image2) outputs a multidimensional tensor, would it be possible to produce a scalar that can be used as a loss. I.e deform image 1 and minimise negative correlation between image1, image2.

asked previously and recommended to ask in this thread, https://github.com/sniklaus/pytorch-pwc/issues/15

[jrenzhile]

@bkvie My thinking is that you can certainly get creative and design a novel loss function, but could you please elaborate "deform image 1" and "negative correlation"?

[bkvie]

@luvegood with deform I mean using STN (spatial transformer network) or some trainable warping/deformation method that would minimize the correlation between images.