Perfect, thanks for the feedback.
Really helpful.
Well, the reason that I am looking on an RGB stereo solution, is the fact that I would like to take advantage of some good AI models for encoding the depth/point-cloud information directly from a dual rgb stream. For example FoundationStereo, BridgeDepth, etc.. that's why I would be interested to check also the process unit of the board (though this is not a deal break). For example, as I understood all the OAK-FFC boards are coming with an RVC2 architecture on-board features, right? Is there anything already, or possibly coming soon with something more powerful like an RVC4 architecture board? Otherwise, the RVC2 architecture I guess can handle at least compression and synchronization.