Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

You should try processing your photo dataset with a NERF based tool. They are much better at rebuilding the 3D structure from set of images.

EDIT: There is this for example https://github.com/nerfstudio-project/nerfstudio



I want the future version of Google Earth or whatever to be the whole globe at a pixel resolution with this kind of technology.


That's inventing details that don't exist in the data though, correct?


Don't think so. Pictures have to be taken from multiple angles with overlaps so that summing them up contain the whole thing.


Thanks so much—I’ll try this out!




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: