Efficient Proxy Raytracer for Optical Systems using Implicit Neural Representations

TL;DR

Ray2Ray introduces an implicit neural representation-based proxy for optical ray tracing, enabling efficient, end-to-end modeling of optical systems with high accuracy, reducing computational complexity compared to traditional surface-by-surface methods.

Contribution

The paper presents Ray2Ray, a novel neural network approach that models optical systems directly, eliminating the need for sequential surface computations and achieving high-precision results.

Findings

Achieved positional errors around 1μm.

Attained angular deviations near 0.01 degrees.

Successfully modeled nine different optical systems.

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 optical systems with greater efficiency, 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. We train Ray2Ray on nine off-the-shelf optical systems, achieving positional errors on the order of 1{\mu}m and angular deviations on the order 0.01 degrees in the estimated output rays. Our work highlights the potential of neural representations as a proxy for optical raytracer.