What's the difference in NeRF from a classical photogrammetry pointcloud workflow? It seems like the representation and outputs are identical.
Why would you prefer NeRF to photogrammetry? Or vice versa?
Why would you prefer NeRF to photogrammetry? Or vice versa?
For example, most NeRF implementations recommend the use of COLMAP (traditionally a photogrammetry tool) to obtain camera positions/rotations that are used alongside their images. So this multi-view stereo step is shared between both NeRF (except a few research works that also optimize for camera positions/rotations through a neural network) and photogrammetry.
After the multi-view stereo step in NeRF you train a neural renderer, while in photogrammetry you would run a multi-view geometry step/package that uses more traditional optimization algorithms.
The expected output of both techniques is slightly different. NeRF produces renderings and can optionally export a mesh (using the marching cubes algorithm). Photogrammetry produces meshes and in the process might render the scene for editting purposes.
They also are proving to be faster, more accurate, etc
The input data is the same. Nerfs have the chance of requiring less input data.