Re:NeRF in the Wild: reconstructing 3D scenes from internet ...
by Ut_Pwnsim on Thursday August 06, 2020 @04:55PM
(#24075372)
What is the precision required (or used in your datasets) for camera position and angles? Is the geotagging in the images from common cellphones and smart cameras enough? Were they back-calculated using some other method from non- or poorly-georeferenced images?
[ Parent
| on HN ]
Re:NeRF in the Wild: reconstructing 3D scenes from internet ...
by duckworthd on Thursday August 06, 2020 @05:04PM
(#24075452)
It's hard for me to say how precise camera position and direction needs to be. We use COLMAP to estimate both via multi-view stereo.