I have been working on a holographic camera, but the ultra-cheap pinhole cameras I chose for the array have two issues: the exposure can't be controlled and the lenses are poorly aligned. I can calibrate away most lens aberrations with OpenCV, but some of the outliers have so much cropping that I am discarding 75% of my good pixels to get a coherent result. I was considering using NeRFs to reproject the ideal camera angles, but COLMAP is not very tolerant of brightness fluctuations and NeRF training is relatively slow (considering my goal is video). This would be a nice solution to my problem, because I have a comprehensive set of angles to pull context from.