DDNeRF: Depth Distribution Neural Radiance Fields
release_ndcyqqw6zndb3cyj5i44ohua6e
by
David Dadon, Ohad Fried, Yacov Hel-Or
2022
Abstract
In recent years, the field of implicit neural representation has progressed
significantly. Models such as neural radiance fields (NeRF), which uses
relatively small neural networks, can represent high-quality scenes and achieve
state-of-the-art results for novel view synthesis. Training these types of
networks, however, is still computationally very expensive. We present depth
distribution neural radiance field (DDNeRF), a new method that significantly
increases sampling efficiency along rays during training while achieving
superior results for a given sampling budget. DDNeRF achieves this by learning
a more accurate representation of the density distribution along rays. More
specifically, we train a coarse model to predict the internal distribution of
the transparency of an input volume in addition to the volume's total density.
This finer distribution then guides the sampling procedure of the fine model.
This method allows us to use fewer samples during training while reducing
computational resources.
In text/plain
format
Archived Files and Locations
application/pdf 11.3 MB
file_mrhnycteovg5devukt4vgpz6je
|
arxiv.org (repository) web.archive.org (webarchive) |
2203.16626v1
access all versions, variants, and formats of this works (eg, pre-prints)