Ref-NeRF: Structured View-Dependent Appearance for Neural Radiance Fields
IEEE Transactions on Pattern Analysis and Machine Intelligence · 2025-11 · 47 (11) · 9426-9437
DOI: 10.1109/tpami.2024.3360018 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2025-11. Verfasst von Dor Verbin und 5 weiteren Autor:innen. Die Arbeit wurde bisher 30-mal zitiert (Crossref) und nennt 49 Literaturangaben. Gefördert von: National Science Foundation.
Abstract (Originalsprache)
Neural Radiance Fields (NeRF) is a popular view synthesis technique that represents a scene as a continuous volumetric function, parameterized by multilayer perceptrons that provide the volume density and view-dependent emitted radiance at each location. While NeRF-based techniques excel at representing fine geometric structures with smoothly varying view-dependent appearance, they often fail to accurately capture and reproduce the appearance of glossy surfaces. We address this limitation by introducing Ref-NeRF, which replaces NeRF's parameterization of view-dependent outgoing radiance with a representation of reflected radiance and structures this function using a collection of spatially-varying scene properties. We show that together with a regularizer on normal vectors, our model significantly improves the realism and accuracy of specular reflections. Furthermore, we show that our model's internal representation of outgoing radiance is interpretable and useful for scene editing.
Förderung
- National Science Foundation
Zitieren
APA
Verbin, D., Hedman, P., Mildenhall, B., Zickler, T., Barron, J. T., & Srinivasan, P. P. (2025). Ref-NeRF: Structured View-Dependent Appearance for Neural Radiance Fields. IEEE Transactions on Pattern Analysis and Machine Intelligence, 47(11), 9426-9437. https://doi.org/10.1109/tpami.2024.3360018
Vancouver
Verbin D, Hedman P, Mildenhall B, Zickler T, Barron JT, Srinivasan PP. Ref-NeRF: Structured View-Dependent Appearance for Neural Radiance Fields. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2025;47(11):9426-9437. doi:10.1109/tpami.2024.3360018
BibTeX
@article{Verbin2025,
author = {Verbin, Dor and Hedman, Peter and Mildenhall, Ben and Zickler, Todd and Barron, Jonathan T and Srinivasan, Pratul P},
title = {Ref-NeRF: Structured View-Dependent Appearance for Neural Radiance Fields},
journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
year = {2025},
volume = {47},
number = {11},
pages = {9426--9437},
doi = {10.1109/tpami.2024.3360018}
}
EUVIMED