This work portrays several ways in which a pair (triplet) of completely independent 2D data sets, such as regular 2D color pictures or Height fields, are merged into one 3D model, creating an Ortho-picture. The Ortho-picture will look like the first input set from one view and will identify with the second set from an orthogonal view. While techniques to reconstruct 3D geometry from several 2D data sets of the same 2D models are well known, herein we strive to merge pairs of completely independent 2D input data sets. The end result of this effort is a regular 3D model that is automatically synthesized from a pair of two completely independent pictures or 3D objects.
Given the following two pictures:
One can synthesize the following output from two orthogonal views, using zero-dimensional blob primitives:
Output as an animated gif (click on the animation to see a full resolution animation):
One can synthesize similar 3D geometry using long strips instead blobs:
With strips ordered in random, or alternatively along a single diagonal plane:
Colors are possible too while manufacturing a colored version is still an open question:
Output as an animated gif for three (!) images (click on the animation to see a full resolution animation):
See also Dithered Ortho Pictures