Johan Edstedt
Johan Edstedt
Hi! The PCK in pdcnet is on a different subset of megadepth and therefore not directly comparable. As for the confidence estimate, yes it helps, but if you qualitatively look...
Ah, another point is that pdcnet does actually train on megadepth (just different strategy), so I think the conparison is pretty fair.
1. Yes. Typically you would use a few LM optimization steps to improve. This is included in most opencv ransac, not sure about the most basic one. If using LO-RANSAC...
Hi. You would need to rewrite the loss function a bit, but it works just fine for homographies as well. It works with anything that creates a warp.
Quite a few changes. Main ones on the top of my head are, 1. Changes to representation of refiner input, in particular adding local correlation features. 2. Inverse KDE match...
No, you would have to basically look at changes in the source code. The initial uploaded version might even be v2, I don't remember.
Yeah, probably it doesn't matter since you initialize inv_std so that the softplus puts it at 1. Maybe its slightly easier to get a singular distribution (i.e. close to zero...
@Phil26AT I'm interested too!
@Phil26AT great news! What's the score of the ALIKED version om the benchmarks?
Cool, thanks!