Saved in:
Bibliographic Details
Main Authors: Dai, Jun, Chen, Liqun, Yang, Xinge, Hu, Yuyao, Gu, Jinwei, Xue, Tianfan
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2502.04719
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929702220857344
author Dai, Jun
Chen, Liqun
Yang, Xinge
Hu, Yuyao
Gu, Jinwei
Xue, Tianfan
author_facet Dai, Jun
Chen, Liqun
Yang, Xinge
Hu, Yuyao
Gu, Jinwei
Xue, Tianfan
contents Deep optics has emerged as a promising approach by co-designing optical elements with deep learning algorithms. However, current research typically overlooks the analysis and optimization of manufacturing and assembly tolerances. This oversight creates a significant performance gap between designed and fabricated optical systems. To address this challenge, we present the first end-to-end tolerance-aware optimization framework that incorporates multiple tolerance types into the deep optics design pipeline. Our method combines physics-informed modelling with data-driven training to enhance optical design by accounting for and compensating for structural deviations in manufacturing and assembly. We validate our approach through computational imaging applications, demonstrating results in both simulations and real-world experiments. We further examine how our proposed solution improves the robustness of optical systems and vision algorithms against tolerances through qualitative and quantitative analyses. Code and additional visual results are available at openimaginglab.github.io/LensTolerance.
format Preprint
id arxiv_https___arxiv_org_abs_2502_04719
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Tolerance-Aware Deep Optics
Dai, Jun
Chen, Liqun
Yang, Xinge
Hu, Yuyao
Gu, Jinwei
Xue, Tianfan
Computer Vision and Pattern Recognition
Graphics
Deep optics has emerged as a promising approach by co-designing optical elements with deep learning algorithms. However, current research typically overlooks the analysis and optimization of manufacturing and assembly tolerances. This oversight creates a significant performance gap between designed and fabricated optical systems. To address this challenge, we present the first end-to-end tolerance-aware optimization framework that incorporates multiple tolerance types into the deep optics design pipeline. Our method combines physics-informed modelling with data-driven training to enhance optical design by accounting for and compensating for structural deviations in manufacturing and assembly. We validate our approach through computational imaging applications, demonstrating results in both simulations and real-world experiments. We further examine how our proposed solution improves the robustness of optical systems and vision algorithms against tolerances through qualitative and quantitative analyses. Code and additional visual results are available at openimaginglab.github.io/LensTolerance.
title Tolerance-Aware Deep Optics
topic Computer Vision and Pattern Recognition
Graphics
url https://arxiv.org/abs/2502.04719