English

Degradation-Modeled Multipath Diffusion for Tunable Metalens Photography

Computer Vision and Pattern Recognition 2025-07-01 v1

Abstract

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/.

Keywords

Cite

@article{arxiv.2506.22753,
  title  = {Degradation-Modeled Multipath Diffusion for Tunable Metalens Photography},
  author = {Jianing Zhang and Jiayi Zhu and Feiyu Ji and Xiaokang Yang and Xiaoyun Yuan},
  journal= {arXiv preprint arXiv:2506.22753},
  year   = {2025}
}
R2 v1 2026-07-01T03:37:35.040Z