Ray Tracing with Neural Networks

Introduction

Accurate simulation of imaging systems is crucial for enabling cost-effective and rapid design processes and training machine learning algorithms. Such simulation tools typically incorporate the full imaging pipeline, including the scene, camera optics, and image sensor. However, the proprietary nature of lens designs often leads manufacturers to withhold specific details, posing a challenge for accurate simulation. To address this challenge, Goossens et al. (2022) propose a solution that leverages Zemax black-box lens models. At the core of this method is the Ray Transfer Function (RTF), which characterizes how the position and angle of a ray entering a lens determine its exit position and angle, providing a practical approach to lens modeling without exposing proprietary design information. Goossens et al., modeled the RTF using a polynomial fitting and showed promising results as in [1]. The idea of this project is to explore the potential of neural networks to approximate the ray transfer function and enable efficient, high-fidelity ray tracing without the need for detailed lens specifications. As neural networks have demonstrated remarkable capabilities in learning complex nonlinear functions, making them a promising candidate for modeling the ray transfer function [2].

Background

1. Dataset Generation using Zemax

2. Polynomial Estimation of Ray-Transfer Functions In a general form, the RTF consists of six independent variables, $x,y,z,dx,dy,dz$.

Methods

1. Network Architecture

2. Loss Function and Training Details

Results

1. Ray Tracing

2. Ray Classification

3. Remaining Issue: Imbalanced Dataset

References

[1] Thomas Goossens, Zheng Lyu, Jamyuen Ko, Gordon C. Wan, Joyce Farrell, and Brian Wandell, "Ray-transfer functions for camera simulation of 3D scenes with hidden lens design," Opt. Express 30, 24031-24047 (2022).

[2] Ian Goodfellow and Yoshua Bengio and Aaron Courville, "Deep Learning," MIT Press (2016), http://www.deeplearningbook.org.