Physically Based Neural Bidirectional Reflectance Distribution Function
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910683802632192 |
|---|---|
| author | Zhou, Chenliang Sztrajman, Alejandro Rainer, Gilles Zhong, Fangcheng Gokbudak, Fazilet Guo, Zhilin Xia, Weihao Mantiuk, Rafal Oztireli, Cengiz |
| author_facet | Zhou, Chenliang Sztrajman, Alejandro Rainer, Gilles Zhong, Fangcheng Gokbudak, Fazilet Guo, Zhilin Xia, Weihao Mantiuk, Rafal Oztireli, Cengiz |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_02347 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Physically Based Neural Bidirectional Reflectance Distribution Function Zhou, Chenliang Sztrajman, Alejandro Rainer, Gilles Zhong, Fangcheng Gokbudak, Fazilet Guo, Zhilin Xia, Weihao Mantiuk, Rafal Oztireli, Cengiz Graphics Computer Vision and Pattern Recognition Machine Learning 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. |
| title | Physically Based Neural Bidirectional Reflectance Distribution Function |
| topic | Graphics Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2411.02347 |