Good evening, I am currently developing an application as part of my thesis project that uses the new Object Capture API in RealityKit. Unfortunately, the official Apple documentation does not state which technical algorithms are used internally in Object Capture for 3D reconstruction. It is only said that the general technology of photogrammetry is used. Is object capture essentially based on the following technical processes: "Scale-invariant feature transform (SIFT)", "Random sample consensus (RANSAC)", "Structure from Motion (SfM)", "Bundle adjustment" and / or "Multi-View Stereo (MVS)"? This information would be very helpful for my thesis and the development of the app. Does anyone have official information on what technical algorithms are used? :) Any information is helpful. Thanks.
RealityKit Object Capture Photogrammetry Algorithms
Yes this is very good!