I wondered that myself (wishing Canoma had never been sold to Adobe) and looking at the spec sheets for Realsence makes you think it might be capable assuming it could output what it actually sees but I'm guessing there's a distinct difference between what it actually sees and what the marketing brochures show. I'm thinking the Realsence visual information might be more reminiscent of a laser scanned point cloud. That said there doesn't seem to be any way to output the Realsense vision data so probably just a pipe dream.
Yes exactly! Looking at the spec sheets I would certainly think it's possible but you're right, the main issue is outputting the realsense data. Oh well, it's nice to dream.