tailortrik0

I am trying to combine two images to a gl render.

CV tracks points inside of both images and compares their relative distance to the other image.

this difference value for each pixel becomes the depth mask for the image.

basically doing the same thing our eye does when it sees depth

I feel like this could potentially be used with live stereo video.

it seems simple enough but i'm still not experienced enough to know the best way to do it.

I am trying to combine two images to a gl render.
CV tracks points inside of both images and compares their relative distance to the other image.

stereoscopic images into obj depth