Re:NeRF in the Wild: reconstructing 3D scenes from internet ...
by mey on Thursday August 06, 2020 @05:28PM
(#24075645)
The former. Once the scene is synthesized, I figure that is where any dynamic output would occur. Although that raises an interesting thought of using the NeRF modeling to paint out certain things in potentially live video.
If the question is, "can you reconstruct a (static) scene from the frames in a video?", the answer is yes!
If the question is, "can you reconstruct a scene with people and other moving objects, and model them moving around too?", the answer is not yet.