Depth-guided NeRF Training via Earth Mover's Distance

arXiv:2403.13206v1 Announce Type: new
Abstract: Neural Radiance Fields (NeRFs) are trained to minimize the rendering loss of predicted viewpoints. However, the photometric loss often does not provide enough information to disambiguate between different possible geometries yielding the same image. Previous work has thus incorporated depth supervision during NeRF training, leveraging dense predictions from pre-trained depth networks as pseudo-ground truth. While these depth priors are assumed to be perfect once filtered for noise, in practice, their accuracy is more challenging to …

abstract arxiv cs.ai cs.cv earth fields however image information loss mover nerf neural radiance fields predictions rendering supervision training type via work