EUVIMEDEUVIMED entdecken
Crossref

Probabilistic-Based Learning for Joint Light Field Image Compression and Enhancement Under Low-Light Conditions

Deyang Liu, Jimin Wang, Yifan Mao, Mounir Kaaniche, Xiaofei Zhou, Gangyi Jiang, Caifeng Shan

IEEE Transactions on Image Processing · 2026 · 35 · 7375-7390

DOI: 10.1109/tip.2026.3709463 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Image Processing, 2026. Verfasst von Deyang Liu und 6 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 61 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Anhui Provincial University Natural Science Research Project, Taishan Scholar Foundation of Shandong Province.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Light field (LF) imaging has attracted increasing research interest in challenging illumination conditions due to its ability to provide rich spatial and angular cues. However, such data present dual challenges: 1) the inherent multi-view structure introduces substantial data redundancy, creating high demands for efficient compression; 2) the insufficient illumination leads to severe quality degradation, which weakens inter-view consistency and visual perception. To address these coupled factors, we propose a Probabilistic-based learning for joint LF image compression and enhancement under low-light conditions (PrL-LFCE). The framework unifies structure-aware compression and feature enhancement mechanisms by introducing learnable probabilistic modeling into both feature coupling and latent distribution estimation to adaptively handle the uncertainty induced by illumination degradation and compression-related information loss. Specifically, we design a probability-based multi-directional feature coupling module that dynamically balances structural preservation and redundancy reduction across multiple directionally arranged sub-aperture images. Moreover, we introduce a swin-gated enhancement module that suppresses noise and highlights structurally salient regions in compression-aware feature representations through attention-guided gating. Extensive experiments show that PrL-LFCE consistently outperforms state-of-the-art methods, achieving at least 34.86% bitrate savings while maintaining excellent visual quality, demonstrating a strong joint compression and enhancement capability.

Förderung

  • National Natural Science Foundation of China
  • Anhui Provincial University Natural Science Research Project
  • Taishan Scholar Foundation of Shandong Province
  • Natural Science Foundation of Anhui Province
  • Anhui Province High-Level Talents Introduction and Cultivation Project

Zitieren

APA

Liu, D., Wang, J., Mao, Y., Kaaniche, M., Zhou, X., Jiang, G., & Shan, C. (2026). Probabilistic-Based Learning for Joint Light Field Image Compression and Enhancement Under Low-Light Conditions. IEEE Transactions on Image Processing, 35, 7375-7390. https://doi.org/10.1109/tip.2026.3709463

Vancouver

Liu D, Wang J, Mao Y, Kaaniche M, Zhou X, Jiang G, et al. Probabilistic-Based Learning for Joint Light Field Image Compression and Enhancement Under Low-Light Conditions. IEEE Transactions on Image Processing. 2026;35:7375-7390. doi:10.1109/tip.2026.3709463

BibTeX
@article{Liu2026,
  author = {Liu, Deyang and Wang, Jimin and Mao, Yifan and Kaaniche, Mounir and Zhou, Xiaofei and Jiang, Gangyi and Shan, Caifeng},
  title = {Probabilistic-Based Learning for Joint Light Field Image Compression and Enhancement Under Low-Light Conditions},
  journal = {IEEE Transactions on Image Processing},
  year = {2026},
  volume = {35},
  pages = {7375--7390},
  doi = {10.1109/tip.2026.3709463}
}
Kostenlos starten →