Physically Based Neural Bidirectional Reflectance Distribution Function

Autor:	Zhou, Chenliang, Sztrajman, Alejandro, Rainer, Gilles, Zhong, Fangcheng, Gokbudak, Fazilet, Guo, Zhilin, Xia, Weihao, Mantiuk, Rafal, Oztireli, Cengiz
Rok vydání:	2024
Předmět:	Computer Science - Graphics Computer Science - Computer Vision and Pattern Recognition Computer Science - Machine Learning
Druh dokumentu:	Working Paper
Popis:	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 reconstructs real-world materials while uniquely enforcing physical properties for realistic BRDFs, specifically Helmholtz reciprocity via reparametrization and energy passivity 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 color 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.
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2411.02347 Zobrazit plný text záznamu View this record from Arxiv