NeRF in the Wild: reconstructing 3D scenes from internet photography

Re:NeRF in the Wild: reconstructing 3D scenes from internet ... by _visgean on Thursday August 06, 2020 @02:30PM (#24073958)

Is the model able to capture the underlining geometry? E.g. If I have a pillar part of which was not visible at any training point is it able to reconstruct that part?

[ Parent | on HN ]

Re:NeRF in the Wild: reconstructing 3D scenes from internet ... by duckworthd on Thursday August 06, 2020 @04:03PM (#24074865)

The model is trained to reconstruct what is observed, but not what is obscured. If you look closely at our videos, you'll notice some parts of the scene are blurry -- those parts weren't seen often enough to learn well. If you look at parts of the scene not observed at all, I'm not sure what you'd find.

[ Parent | on HN ]