Probabilistic NeRF for 3D Shape Recovery in Scattered Medium

Yoshiki Ono, Fumihiko Sakaue, Jun Sato

2024

Abstract

This research proposes a method for analyzing scene information including the characteristics of the medium by representing the space where objects and scattering media such as fog and smoke exist using the NeRF (Neural Radiance Fields) (Mildenhall et al., 2020) representation method of light ray fields. In this study, we focus on the fact that the behavior of rays inside a scattering medium can be expressed probabilistically, and show a method for rendering an image that changes in a probabilistic manner from only a single ray, rather than the entire scattering. By combining this method with a scene representation using the stochastic gradient descent method and a neural network, we show that it is possible to analyze scene information without generating images that directly render light scattering.

Paper Citation

in Harvard Style

Ono Y., Sakaue F. and Sato J. (2024). Probabilistic NeRF for 3D Shape Recovery in Scattered Medium. In Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 3: VISAPP; ISBN 978-989-758-679-8, SciTePress, pages 779-785. DOI: 10.5220/0012473300003660

in Bibtex Style

@conference{visapp24,
author={Yoshiki Ono and Fumihiko Sakaue and Jun Sato},
title={Probabilistic NeRF for 3D Shape Recovery in Scattered Medium},
booktitle={Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 3: VISAPP},
year={2024},
pages={779-785},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012473300003660},
isbn={978-989-758-679-8},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 3: VISAPP
TI - Probabilistic NeRF for 3D Shape Recovery in Scattered Medium
SN - 978-989-758-679-8
AU - Ono Y.
AU - Sakaue F.
AU - Sato J.
PY - 2024
SP - 779
EP - 785
DO - 10.5220/0012473300003660
PB - SciTePress