U 2 -LFOR: A Two-Stage U 2 Network for Light-Field Occlusion Removal

Mostafa Farouk Senussi, Mahmoud Abdalla, Mahmoud SalahEldin Kasem, Mohamed Mahmoud and Hyun-Soo Kang ()
Additional contact information
Mostafa Farouk Senussi: Department of Information and Communication Engineering, School of Electrical and Computer Engineering, Chungbuk National University, Cheongju-si 28644, Republic of Korea
Mahmoud Abdalla: Department of Information and Communication Engineering, School of Electrical and Computer Engineering, Chungbuk National University, Cheongju-si 28644, Republic of Korea
Mahmoud SalahEldin Kasem: Department of Information and Communication Engineering, School of Electrical and Computer Engineering, Chungbuk National University, Cheongju-si 28644, Republic of Korea
Mohamed Mahmoud: Department of Information and Communication Engineering, School of Electrical and Computer Engineering, Chungbuk National University, Cheongju-si 28644, Republic of Korea
Hyun-Soo Kang: Department of Information and Communication Engineering, School of Electrical and Computer Engineering, Chungbuk National University, Cheongju-si 28644, Republic of Korea

Mathematics, 2025, vol. 13, issue 17, 1-21

Abstract: Light-field (LF) imaging transforms occlusion removal by using multiview data to reconstruct hidden regions, overcoming the limitations of single-view methods. However, this advanced capability often comes at the cost of increased computational complexity. To overcome this, we propose the U 2 -LFOR network, an end-to-end neural network designed to remove occlusions in LF images without compromising performance, addressing the inherent complexity of LF imaging while ensuring practical applicability. The architecture employs Residual Atrous Spatial Pyramid Pooling (ResASPP) at the feature extractor to expand the receptive field, capture localized multiscale features, and enable deep feature learning with efficient aggregation. A two-stage U 2 -Net structure enhances hierarchical feature learning while maintaining a compact design, ensuring accurate context recovery. A dedicated refinement module, using two cascaded residual blocks (ResBlock), restores fine details to the occluded regions. Experimental results demonstrate its competitive performance, achieving an average Peak Signal-to-Noise Ratio (PSNR) of 29.27 dB and Structural Similarity Index Measure (SSIM) of 0.875, which are two widely used metrics for evaluating reconstruction fidelity and perceptual quality, on both synthetic and real-world LF datasets, confirming its effectiveness in accurate occlusion removal.

Keywords: light-field imaging; occlusion removal; U2-Net; Residual Atrous Spatial Pyramid Pooling (ResASPP); residual block (ResBlock) (search for similar items in EconPapers)
JEL-codes: C (search for similar items in EconPapers)
Date: 2025
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2227-7390/13/17/2748/pdf (application/pdf)
https://www.mdpi.com/2227-7390/13/17/2748/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jmathe:v:13:y:2025:i:17:p:2748-:d:1733059

Access Statistics for this article

Mathematics is currently edited by Ms. Emma He

More articles in Mathematics from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().