1. Cameras as Rays: Pose Estimation via Ray Diffusion, ICLR 2024
2. 2.7 deep image matching

Structure from Motion (SfM) and MultiView Stereo (MVS)

Bundler -> CMVS -> PMVS2

1. You should ALWAYS use CMVS after Bundler and before PMVS2
   1. Specifically, CMVS appears to be the best-in-show MVS tool,
   2. Bundler seems to be one of the better open source SFM tools out there.
2. MVS requiring camera parameters to run, which is estimated (output) by SfM. SfM only gives a coarse 3D output, whereas PMVS2 gives a more dense output, and finally CMVS is there to circumvent some limitations of PMVS2.

https://colmap.github.io/

COLMAP is a general-purpose Structure-from-Motion (SfM) and Multi-View Stereo (MVS) pipeline with a graphical and command-line interface.