[sorenjan]

Good monocular depth estimation is crucial if you want to make a 3D representation from a single image. Ordinarily you have images from several camera poses and can create the gaussian splats using triangulation, with a single image you have to guess z position for them.

[Someone]

For selfies, I think iPhones with Face ID use the TrueDepth camera hardware to measure Z position. That’s not full camera resolution, but it will definitely help.