Physically Based Neural BRDF: A Framework for Physically Correct Material Reconstruction, Generation and Editing
Computer Graphics Forum · 15.05.2026
DOI: 10.1111/cgf.70500 ↗Kurz gefasst
Fachartikel in der Zeitschrift Computer Graphics Forum, online erschienen am 15.05.2026. Verfasst von C. Zhou und 8 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 79 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
We introduce the physically based neural bidirectional reflectance distribution function (PBNBRDF) , a novel continuous representation for material appearance based on neural fields. Our model accurately performs real‐world material reconstruction, generation and editing, while uniquely enforcing physical properties for realistic BRDFs: Helmholtz reciprocity via reparametrisation and energy conservation via efficient analytical integration. We conduct a systematic analysis demonstrating the benefits of adhering to these physical laws on the visual quality of reconstructed materials. Additionally, we enhance the colour accuracy of neural BRDFs by introducing chromaticity enforcement supervising the norms of RGB channels. Through both qualitative and quantitative experiments on multiple databases of measured real‐world BRDFs, we show that adhering to these physical constraints enables neural fields to more faithfully and stably represent the original data and achieve higher rendering quality.
Zitieren
APA
Zhou, C., Sztrajman, A., Rainer, G., Zhong, F., Gokbudak, F., Guo, Z., Xia, W., Mantiuk, R. K., & Oztireli, C. (2026). Physically Based Neural BRDF: A Framework for Physically Correct Material Reconstruction, Generation and Editing. Computer Graphics Forum. https://doi.org/10.1111/cgf.70500
Vancouver
Zhou C, Sztrajman A, Rainer G, Zhong F, Gokbudak F, Guo Z, et al. Physically Based Neural BRDF: A Framework for Physically Correct Material Reconstruction, Generation and Editing. Computer Graphics Forum. 2026. doi:10.1111/cgf.70500
BibTeX
@article{Zhou2026,
author = {Zhou, C. and Sztrajman, A. and Rainer, G. and Zhong, F. and Gokbudak, F. and Guo, Z. and Xia, W. and Mantiuk, R. K. and Oztireli, C.},
title = {Physically Based Neural BRDF: A Framework for Physically Correct Material Reconstruction, Generation and Editing},
journal = {Computer Graphics Forum},
year = {2026},
doi = {10.1111/cgf.70500}
}
EUVIMED