Probabilistic Prior-Driven Attention Mechanism Based on a Diffusion Model for Imaging Through Atmospheric Turbulence
Electronics · 08.07.2026 · 15 (14) · 3001
DOI: 10.3390/electronics15143001 ↗Kurz gefasst
Fachartikel in der Zeitschrift Electronics, online erschienen am 08.07.2026. Verfasst von Yingping Sun und 6 weiteren Autor:innen. Die Arbeit nennt 44 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Atmospheric turbulence introduces severe spatial and geometric distortions, challenging traditional image restoration methods. We propose the Probabilistic Prior Turbulence Removal Network (PPTRN), which combines probabilistic diffusion-based prior modeling with Transformer-driven feature extraction to address this issue. PPTRN employs a two-stage approach: first, a latent encoder and Transformer are jointly trained on clear images to establish robust feature representations. Then, a Denoising Diffusion Probabilistic Model (DDPM) models prior distributions over latent vectors, guiding the Transformer in capturing diverse feature variations essential for restoration. A key innovation in PPTRN is the Probabilistic Prior-Driven Cross-Attention mechanism, which integrates the DDPM-generated prior with feature embeddings to reduce artifacts and enhance spatial coherence. Extensive experiments validate that PPTRN significantly improves restoration quality on turbulence-degraded images, setting a new benchmark in clarity and structural fidelity.
Zitieren
APA
Sun, Y., Bai, D., Liu, Y., Wang, D., Miao, R., Qin, Z., & Wang, H. (2026). Probabilistic Prior-Driven Attention Mechanism Based on a Diffusion Model for Imaging Through Atmospheric Turbulence. Electronics, 15(14), 3001. https://doi.org/10.3390/electronics15143001
Vancouver
Sun Y, Bai D, Liu Y, Wang D, Miao R, Qin Z, et al. Probabilistic Prior-Driven Attention Mechanism Based on a Diffusion Model for Imaging Through Atmospheric Turbulence. Electronics. 2026;15(14):3001. doi:10.3390/electronics15143001
BibTeX
@article{Sun2026,
author = {Sun, Yingping and Bai, Dengtian and Liu, Yan and Wang, Dong and Miao, Rongzhen and Qin, Zihan and Wang, Hongwei},
title = {Probabilistic Prior-Driven Attention Mechanism Based on a Diffusion Model for Imaging Through Atmospheric Turbulence},
journal = {Electronics},
year = {2026},
volume = {15},
number = {14},
pages = {3001},
doi = {10.3390/electronics15143001}
}
EUVIMED