Academic Journal
أعرض في EDS

High-Fidelity Light Field Reconstruction Method Using View-Selective Angular Feature Extraction

التفاصيل البيبلوغرافية
العنوان: High-Fidelity Light Field Reconstruction Method Using View-Selective Angular Feature Extraction
المؤلفون: Shubo Zhou, Xue-Qin Jiang, Xiaoming Ding, Rong Huang
المصدر: IEEE Access, Vol 11, Pp 31157-31166 (2023)
بيانات النشر: IEEE, 2023.
سنة النشر: 2023
المجموعة: LCC:Electrical engineering. Electronics. Nuclear engineering
مصطلحات موضوعية: Light field reconstruction, light field imaging, view-selective angular feature, convolutional neural network, Electrical engineering. Electronics. Nuclear engineering, TK1-9971
الوصف: Deep learning (DL) provides an effective approach for light field (LF) reconstruction that aims to synthesize novel views from sparsely-sampled views. However, it is challenging to address domain asymmetry when adopting spatial-angular interaction LF reconstruction methods. To overcome this problem, a view-selective angular feature extraction block (VS-LFAFE) is proposed to obtain full-resolution angular features that enumerate whole viewpoints in a macropixel. By applying the VS-LFAFE, a novel LF reconstruction method is proposed, consisting of two subblocks: a spatial-angular feature extraction and fusion block, and an angular upsampling block. Experimental results demonstrate the effectiveness of the VS-LFAFE, and validate that the proposed method can achieve superior performance compared with the state-of-the-art methods.
نوع الوثيقة: article
وصف الملف: electronic resource
اللغة: English
تدمد: 2169-3536
16982568
Relation: https://ieeexplore.ieee.org/document/10081352/; https://doaj.org/toc/2169-3536
DOI: 10.1109/ACCESS.2023.3261967
URL الوصول: https://doaj.org/article/fb6dd87f98f246eea1698256827cd0ed
رقم الانضمام: edsdoj.fb6dd87f98f246eea1698256827cd0ed
قاعدة البيانات: Directory of Open Access Journals
الوصف
تدمد:21693536
16982568
DOI:10.1109/ACCESS.2023.3261967