NeRF--: Neural Radiance Fields Without Known Camera Parameters
Zirui Wang, Shangzhe Wu, Weidi Xie et al.
2021 · arXiv (Cornell University) · 257 citations
Considering the problem of novel view synthesis (NVS) from only a set of 2D images, we simplify the training process of Neural Radiance Field (NeRF) on forward-facing scenes by removing the requirement of known or pre-computed camera parameters, including both intrinsics and 6DoF poses. To this end, we propose NeRF$--$, with three contributions: First, we show that the camera parameters can be jointly optimised as learnable parameters with NeRF training, through a photometric reconstruction; Second, to benchmark the camera parameter estimation and the quality of novel view renderings, we intr…
Explore this paper's citation graph on Constellation.