“Efficient Proxy Raytracer for Optical Systems Using Implicit Neural Representations” by Sinaei, Zheng, Akşit and Iwai
Conference:
Type(s):
Title:
- Efficient Proxy Raytracer for Optical Systems Using Implicit Neural Representations
Session/Category Title:
- Rendering
Presenter(s)/Author(s):
Abstract:
Ray tracing is a widely used technique for modeling optical systems, involving sequential surface-by-surface computations which can be computationally intensive. We propose Ray2Ray, a novel method that leverages implicit neural representations to model ray tracing through optical systems with greater efficiency and performance, eliminating the need for surface-by-surface computations in a single pass end-to-end model. Ray2Ray learns the mapping between rays emitted from a given source and their corresponding rays after passing through a given optical system in a physically accurate manner.
References:
[1] Kaan Akşit, Jeanne Beyazian, Praneeth Chakravarthula, Ziyang Chen, Mustafa Doğa Doğan, Ahmet Hamdi Güzel, Yuta Itoh, Henry Kam, Ahmet Serdar Karadeniz, Koray Kavaklı, Liang Shi, Josef Spjut, David Robert Walton, Jialun Wu, Doğa Yılmaz, Wang Yujie, Runze Zhu, Weijie Xie, Yicheng Zhan, Yiyang Wu, and Xinge Yang. [n. d.]. Odak.
[2] Ethan Tseng, Ali Mosleh, Fahim Mannan, Karl St-Arnaud, Avinash Sharma, Yifan Peng, Alexander Braun, Derek Nowrouzezahrai, Jean-Francois Lalonde, and Felix Heide. 2021. Differentiable compound optics and processing pipeline optimization for end-to-end camera design. ACM Transactions on Graphics (TOG) 40, 2 (2021), 1–19.
[3] Congli Wang, Ni Chen, and Wolfgang Heidrich. 2022. do: A differentiable engine for deep lens design of computational imaging systems. IEEE Transactions on Computational Imaging 8 (2022), 905–916.
[4] Xinge Yang, Qiang Fu, Mohamed Elhoseiny, and Wolfgang Heidrich. 2023. Aberration-aware depth-from-focus. IEEE Transactions on Pattern Analysis and Machine Intelligence (2023).
