Saved in:
Bibliographic Details
Main Authors: Li, Wenyong, Jiang, Qi, Hu, Weijian, Yang, Kailun, Zhang, Zhanjun, Tian, Wenjun, Wang, Kaiwei, Bai, Jian
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2601.03718
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908752443080704
author Li, Wenyong
Jiang, Qi
Hu, Weijian
Yang, Kailun
Zhang, Zhanjun
Tian, Wenjun
Wang, Kaiwei
Bai, Jian
author_facet Li, Wenyong
Jiang, Qi
Hu, Weijian
Yang, Kailun
Zhang, Zhanjun
Tian, Wenjun
Wang, Kaiwei
Bai, Jian
contents Active Alignment (AA) is a key technology for the large-scale automated assembly of high-precision optical systems. Compared with labor-intensive per-model on-device calibration, a digital-twin pipeline built on optical simulation offers a substantial advantage in generating large-scale labeled data. However, complex imaging conditions induce a domain gap between simulation and real-world images, limiting the generalization of simulation-trained models. To address this, we propose augmenting a simulation baseline with minimal unlabeled real-world images captured at random misalignment positions, mitigating the gap from a domain adaptation perspective. We introduce Domain Adaptive Active Alignment (DA3), which utilizes an autoregressive domain transformation generator and an adversarial-based feature alignment strategy to distill real-world domain information via self-supervised learning. This enables the extraction of domain-invariant image degradation features to facilitate robust misalignment prediction. Experiments on two lens types reveal that DA3 improves accuracy by 46% over a purely simulation pipeline. Notably, it approaches the performance achieved with precisely labeled real-world data collected on 3 lens samples, while reducing on-device data collection time by 98.7%. The results demonstrate that domain adaptation effectively endows simulation-trained models with robust real-world performance, validating the digital-twin pipeline as a practical solution to significantly enhance the efficiency of large-scale optical assembly.
format Preprint
id arxiv_https___arxiv_org_abs_2601_03718
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Towards Real-world Lens Active Alignment with Unlabeled Data via Domain Adaptation
Li, Wenyong
Jiang, Qi
Hu, Weijian
Yang, Kailun
Zhang, Zhanjun
Tian, Wenjun
Wang, Kaiwei
Bai, Jian
Computer Vision and Pattern Recognition
Image and Video Processing
Optics
Active Alignment (AA) is a key technology for the large-scale automated assembly of high-precision optical systems. Compared with labor-intensive per-model on-device calibration, a digital-twin pipeline built on optical simulation offers a substantial advantage in generating large-scale labeled data. However, complex imaging conditions induce a domain gap between simulation and real-world images, limiting the generalization of simulation-trained models. To address this, we propose augmenting a simulation baseline with minimal unlabeled real-world images captured at random misalignment positions, mitigating the gap from a domain adaptation perspective. We introduce Domain Adaptive Active Alignment (DA3), which utilizes an autoregressive domain transformation generator and an adversarial-based feature alignment strategy to distill real-world domain information via self-supervised learning. This enables the extraction of domain-invariant image degradation features to facilitate robust misalignment prediction. Experiments on two lens types reveal that DA3 improves accuracy by 46% over a purely simulation pipeline. Notably, it approaches the performance achieved with precisely labeled real-world data collected on 3 lens samples, while reducing on-device data collection time by 98.7%. The results demonstrate that domain adaptation effectively endows simulation-trained models with robust real-world performance, validating the digital-twin pipeline as a practical solution to significantly enhance the efficiency of large-scale optical assembly.
title Towards Real-world Lens Active Alignment with Unlabeled Data via Domain Adaptation
topic Computer Vision and Pattern Recognition
Image and Video Processing
Optics
url https://arxiv.org/abs/2601.03718