Paper summary
Paper summary: FrugalNeRF: Fast Convergence for Extreme Few-shot Novel View Synthesis without Learned Priors
FrugalNeRF trains NeRFs from very few views quickly, using weight-sharing multi-scale voxels and pseudo depth chosen by cross-scale reprojection error, without relying on learned priors.
- Pseudo ground-truth depth is picked by checking which scale best explains the other views (reprojection error).
- Pretrained priors are optional: they can be added without slowing convergence.