Low-light image enhancement based on U-Net and Haar wavelet

التفاصيل البيبلوغرافية
العنوان: Low-light image enhancement based on U-Net and Haar wavelet
المؤلفون: Batziou Elissavet, Konstantinos Ioannidis, Patras Ioannis, Vrochidis Stefanos, Kompatsiaris Ioannis
المصدر: MMM 2023, 29th International Conference on Multimedia Modeling, Bergen, Norway, 9-12 January 2023
بيانات النشر: Zenodo
سنة النشر: 2023
المجموعة: Zenodo
مصطلحات موضوعية: Digital Twin, 3D Representation, Smart Construction
الوصف: This poster was published at the29th International Conference on Multimedia Modeling, organized from the 9th until the 12th of January, 2023 in Bergen, Norway. Abstract Low-light image enhancement has been very popular for improving the visual quality of image representations, while low-light images often require advanced techniques to improve the perception of information for a human viewer. One of the main objectives in increasing the lighting conditions is to retain patterns, texture, and style with minimal deviations from the considered image. To this direction, we propose a low-light image enhancement method with Haar wavelet-based pooling to preserve texture regions and increase their quality
نوع الوثيقة: conference object
اللغة: English
Relation: https://zenodo.org/communities/eu; https://zenodo.org/communities/ashvin2020; https://doi.org/10.5281/zenodo.7669740; https://doi.org/10.5281/zenodo.7669741; oai:zenodo.org:7669741
DOI: 10.5281/zenodo.7669741
الاتاحة: https://doi.org/10.5281/zenodo.7669741
Rights: info:eu-repo/semantics/openAccess ; Creative Commons Attribution 4.0 International ; https://creativecommons.org/licenses/by/4.0/legalcode
رقم الانضمام: edsbas.872684BB
قاعدة البيانات: BASE