Next Article in Journal
ECG Approximate Entropy in the Elderly during Cycling Exercise
Next Article in Special Issue
Bed-Exit Behavior Recognition for Real-Time Images within Limited Range
Previous Article in Journal
EEG Emotion Classification Network Based on Attention Fusion of Multi-Channel Band Features
Previous Article in Special Issue
Sentiment Analysis: An ERNIE-BiLSTM Approach to Bullet Screen Comments
 
 
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
Article

RCA-LF: Dense Light Field Reconstruction Using Residual Channel Attention Networks

1
School of Information and Communication Engineering, College of Electrical and Computer Engineering, Chungbuk National University, Cheongju 28644, Korea
2
Electrical Engineering Department, Faculty of Engineering, Assiut University, Assiut 71515, Egypt
*
Author to whom correspondence should be addressed.
Sensors 2022, 22(14), 5254; https://doi.org/10.3390/s22145254
Submission received: 24 May 2022 / Revised: 9 July 2022 / Accepted: 11 July 2022 / Published: 14 July 2022
(This article belongs to the Special Issue AI Multimedia Applications)

Abstract

Dense multi-view image reconstruction has played an active role in research for a long time and interest has recently increased. Multi-view images can solve many problems and enhance the efficiency of many applications. This paper presents a more specific solution for reconstructing high-density light field (LF) images. We present this solution for images captured by Lytro Illum cameras to solve the implicit problem related to the discrepancy between angular and spatial resolution resulting from poor sensor resolution. We introduce the residual channel attention light field (RCA-LF) structure to solve different LF reconstruction tasks. In our approach, view images are grouped in one stack where epipolar information is available. We use 2D convolution layers to process and extract features from the stacked view images. Our method adopts the channel attention mechanism to learn the relation between different views and give higher weight to the most important features, restoring more texture details. Finally, experimental results indicate that the proposed model outperforms earlier state-of-the-art methods for visual and numerical evaluation.
Keywords: light field reconstruction; based view synthesis; angular super-resolution; channel attention network light field reconstruction; based view synthesis; angular super-resolution; channel attention network

Share and Cite

MDPI and ACS Style

Salem, A.; Ibrahem, H.; Kang, H.-S. RCA-LF: Dense Light Field Reconstruction Using Residual Channel Attention Networks. Sensors 2022, 22, 5254. https://doi.org/10.3390/s22145254

AMA Style

Salem A, Ibrahem H, Kang H-S. RCA-LF: Dense Light Field Reconstruction Using Residual Channel Attention Networks. Sensors. 2022; 22(14):5254. https://doi.org/10.3390/s22145254

Chicago/Turabian Style

Salem, Ahmed, Hatem Ibrahem, and Hyun-Soo Kang. 2022. "RCA-LF: Dense Light Field Reconstruction Using Residual Channel Attention Networks" Sensors 22, no. 14: 5254. https://doi.org/10.3390/s22145254

APA Style

Salem, A., Ibrahem, H., & Kang, H.-S. (2022). RCA-LF: Dense Light Field Reconstruction Using Residual Channel Attention Networks. Sensors, 22(14), 5254. https://doi.org/10.3390/s22145254

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Back to TopTop