“HyperParamBRDF: Fast Parametric Reflectance via Hypernetworks and Physics-Based Simulation” by Beauferris and Loi
Conference:
Type(s):
Title:
- HyperParamBRDF: Fast Parametric Reflectance via Hypernetworks and Physics-Based Simulation
Session/Category Title:
- Rendering
Presenter(s)/Author(s):
Abstract:
HyperParamBRDF uses hypernetworks conditioned on physical parameters to predict nanostructure BRDFs with high fidelity, accelerating appearance evaluation by orders of magnitude compared to simulation and enabling real-time exploration.
References:
[1] Miika Aittala, Tim Weyrich, and Jaakko Lehtinen. 2015. Two-shot SVBRDF capture for stationary materials. ACM Transactions on Graphics (TOG) 34, 4 (2015), 1–11.
[2] Jeppe S Clausen, Emil Højlund-Nielsen, Alexander B Christiansen, Sadegh Yazdi, Meir Grajower, Hesham Taha, Uriel Levy, Anders Kristensen, and N Asger Mortensen. 2014. Plasmonic Metasurfaces for Coloration of Plastic Consumer Products. Nano Letters 14, 8 (2014), 4499–4504.
[3] Fazilet Gokbudak, Alejandro Sztrajman, Chenliang Zhou, Fangcheng Zhong, Rafal Mantiuk, and Cengiz Oztireli. 2024. Hypernetworks for Generalizable BRDF Representation. In European Conference on Computer Vision (ECCV). Springer.
[4] David Ha, Andrew Dai, and Quoc V. Le. 2017. Hypernetworks. In International Conference on Learning Representations (ICLR). https://arxiv.org/abs/1609.09106
[5] Nikola Kovachki, Zongyi Li, Burigede Liu, Kamyar Azizzadenesheli, Kaushik Bhattacharya, Andrew Stuart, and Anima Anandkumar. 2023. Neural Operators: A Foundation Model for Scientific Machine Learning. arxiv:https://arXiv.org/abs/2309.15325 [cs.LG]
[6] Wei Sen Loi. 2021. Multiscale Computational Visualization and Modelling of Optical Nanomaterials and their Application. Ph. D. Dissertation. University of British Columbia.
[7] Wei Sen Loi and Kenneth J. Chau. 2020. Visualization of Angle-dependent Plasmonic Structural Coloration by FDTD-simulated BSDF and Ray-tracing Rendering. In ACM SIGGRAPH 2020 Posters. Association for Computing Machinery, New York, NY, USA, Article 30, 2 pages.
[8] Pingchuan Ma, Zhaocheng Liu, Ziyi Zhu, Zhengyang Geng, and Deming Chen. 2024. PIC2O-Sim: A Physics-Inspired Causality-Aware Dynamic Convolutional Neural Operator for Ultra-Fast Photonic Device FDTD Simulation. arxiv:https://arXiv.org/abs/2406.17810 [physics.optics]
[9] Stefan Alexander Maier. 2007. Plasmonics: Fundamentals and Applications. Springer, New York, NY, USA.
[10] Jiri Navratil, Alan King, Jesus Rios, Georgios Kollias, Ruben Torrado, and Andres Codas. 2019. Accelerating Physics-Based Simulations Using Neural Network Proxies: An Application in Oil Reservoir Modeling. Frontiers in Big Data 2 (2019), 33.
[11] Alejandro Sztrajman, Gilles Rainer, Tobias Ritschel, and Tim Weyrich. 2021. Neural BRDF Representation and Importance Sampling. Computer Graphics Forum 40, 6 (2021), 332–346.
[12] Allen Taflove and Susan C. Hagness. 2005. Computational Electrodynamics: The Finite-Difference Time-Domain Method (3rd ed.). Artech House, Norwood, MA.
[13] Chenliang Zhou, Alejandro Sztrajman, Gilles Rainer, Fangcheng Zhong, Fazilet Gokbudak, Zhilin Guo, Weihao Xia, Rafal Mantiuk, and Cengiz Oztireli. 2024. Physically Based Neural Bidirectional Reflectance Distribution Function. arxiv:https://arXiv.org/abs/2411.02347 [cs.GR]
