Saved in:
Bibliographic Details
Main Authors: Zhang, Jianing, Zhu, Jiayi, Ji, Feiyu, Yang, Xiaokang, Yuan, Xiaoyun
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2506.22753
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916814680752128
author Zhang, Jianing
Zhu, Jiayi
Ji, Feiyu
Yang, Xiaokang
Yuan, Xiaoyun
author_facet Zhang, Jianing
Zhu, Jiayi
Ji, Feiyu
Yang, Xiaokang
Yuan, Xiaoyun
contents Metalenses offer significant potential for ultra-compact computational imaging but face challenges from complex optical degradation and computational restoration difficulties. Existing methods typically rely on precise optical calibration or massive paired datasets, which are non-trivial for real-world imaging systems. Furthermore, a lack of control over the inference process often results in undesirable hallucinated artifacts. We introduce Degradation-Modeled Multipath Diffusion for tunable metalens photography, leveraging powerful natural image priors from pretrained models instead of large datasets. Our framework uses positive, neutral, and negative-prompt paths to balance high-frequency detail generation, structural fidelity, and suppression of metalens-specific degradation, alongside \textit{pseudo} data augmentation. A tunable decoder enables controlled trade-offs between fidelity and perceptual quality. Additionally, a spatially varying degradation-aware attention (SVDA) module adaptively models complex optical and sensor-induced degradation. Finally, we design and build a millimeter-scale MetaCamera for real-world validation. Extensive results show that our approach outperforms state-of-the-art methods, achieving high-fidelity and sharp image reconstruction. More materials: https://dmdiff.github.io/.
format Preprint
id arxiv_https___arxiv_org_abs_2506_22753
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Degradation-Modeled Multipath Diffusion for Tunable Metalens Photography
Zhang, Jianing
Zhu, Jiayi
Ji, Feiyu
Yang, Xiaokang
Yuan, Xiaoyun
Computer Vision and Pattern Recognition
Metalenses offer significant potential for ultra-compact computational imaging but face challenges from complex optical degradation and computational restoration difficulties. Existing methods typically rely on precise optical calibration or massive paired datasets, which are non-trivial for real-world imaging systems. Furthermore, a lack of control over the inference process often results in undesirable hallucinated artifacts. We introduce Degradation-Modeled Multipath Diffusion for tunable metalens photography, leveraging powerful natural image priors from pretrained models instead of large datasets. Our framework uses positive, neutral, and negative-prompt paths to balance high-frequency detail generation, structural fidelity, and suppression of metalens-specific degradation, alongside \textit{pseudo} data augmentation. A tunable decoder enables controlled trade-offs between fidelity and perceptual quality. Additionally, a spatially varying degradation-aware attention (SVDA) module adaptively models complex optical and sensor-induced degradation. Finally, we design and build a millimeter-scale MetaCamera for real-world validation. Extensive results show that our approach outperforms state-of-the-art methods, achieving high-fidelity and sharp image reconstruction. More materials: https://dmdiff.github.io/.
title Degradation-Modeled Multipath Diffusion for Tunable Metalens Photography
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2506.22753