Polarization Uncertainty-Guided Diffusion Model for Color Polarization Image Demosaicking
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (8) · 6028-6036
DOI: 10.1609/aaai.v40i8.37526 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Chenggong Li und 3 weiteren Autor:innen. Die Arbeit wurde bisher 4-mal zitiert (Crossref).
Abstract (Originalsprache)
Color polarization demosaicking (CPDM) aims to reconstruct full-resolution polarization images of four directions from the color-polarization filter array (CPFA) raw image. Due to the challenge of predicting numerous missing pixels and the scarcity of high-quality training data, existing network-based methods, despite effectively recovering scene intensity information, still exhibit significant errors in reconstructing polarization characteristics (degree of polarization, DOP, and angle of polarization, AOP). To address this problem, we introduce the image diffusion prior from text-to-image (T2I) models to overcome the performance bottleneck of network-based methods, with the additional diffusion prior compensating for limited representational capacity caused by restricted data distribution. To effectively leverage the diffusion prior, we explicitly model the polarization uncertainty during reconstruction and use uncertainty to guide the diffusion model in recovering high error regions. Extensive experiments demonstrate that the proposed method accurately recovers scene polarization characteristics with both high fidelity and strong visual perception.
Zitieren
APA
Li, C., Luo, Y., Zhang, J., & Yang, D. (2026). Polarization Uncertainty-Guided Diffusion Model for Color Polarization Image Demosaicking. Proceedings of the AAAI Conference on Artificial Intelligence, 40(8), 6028-6036. https://doi.org/10.1609/aaai.v40i8.37526
Vancouver
Li C, Luo Y, Zhang J, Yang D. Polarization Uncertainty-Guided Diffusion Model for Color Polarization Image Demosaicking. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(8):6028-6036. doi:10.1609/aaai.v40i8.37526
BibTeX
@article{Li2026,
author = {Li, Chenggong and Luo, Yidong and Zhang, Junchao and Yang, Degui},
title = {Polarization Uncertainty-Guided Diffusion Model for Color Polarization Image Demosaicking},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {8},
pages = {6028--6036},
doi = {10.1609/aaai.v40i8.37526}
}
EUVIMED