Hacker News new | ask | show | jobs
by pj_mukh 1519 days ago
Well now I'm curious, is the claim that photoreal-ness doesn't matter when training network for the real world. Weird.
1 comments

Removing lighting before object recognition may be a separate step, yes. But in this case it's just that their goal is to scan objects, shapes as such, and not intrinsic properties of their constituent materials (such as specularity).