search

CompVis / geometry-free-view-synthesis

Is a geometric model required to synthesize novel views from a single image?
https://arxiv.org/abs/2104.07652
MIT License
369 stars 34 forks source link

Why use inverse of intrinsics matrix? #14

Open alextrevithick opened 2 years ago

alextrevithick commented 2 years ago

I notice that in the multiembedder, the inverse intrinsic matrix is also included. Since this information should be already determined by K, why is this also used? Did you notice some improvement?

Thanks

alextrevithick commented 2 years ago

I actually notice that there is K_dst and K_inv_src in the kwargs. However, following the code, I found that K_dst is just K_src. Is this just because the intrinsics are assumed to be the same in every scene?