The 3D image generated by Im2Im may not be displayed when the viewpoint is moved, ... depth information is inferred from a single image, and a grid-like mesh sheet is pasted based on this information.

The most detailed images, to date, reveal a pervasive 3D grid structure with no diagonals, say scientists funded by the National Institutes of Health.

SLAT uses a sparse 3D grid of 64 ^3 = approximately 260,000 voxels as its underlying structure, although only about 20,000 of these voxels are actually used, located on the surface of the 3D object.