We learn a scene through two alternating stages. Scene fitting optimizes our K-Planes representation to reproduce the images in the training set, as traditionally done in neural rendering techniques. Scene refining finetunes a pre-trained prior and infers a new refined K-Planes representation, which will subsequently be corrected by scene fitting.
@article{kassab2023refinedfields,
title={RefinedFields: Radiance Fields Refinement for Unconstrained Scenes},
author={Kassab, Karim and Schnepf, Antoine and Franceschi, Jean-Yves and Caraffa, Laurent and Mary, Jeremie and Gouet-Brunet, Val{\'e}rie},
journal={arXiv preprint arXiv:2312.00639},
year={2023}
}