Light Field Image Super-Resolution Using Deep Residual Networks on Lenslet Images
Author:
Salem Ahmed12ORCID, Ibrahem Hatem1ORCID, Kang Hyun-Soo1ORCID
Affiliation:
1. School of Information and Communication Engineering, College of Electrical and Computer Engineering, Chungbuk National University, Cheongju 28644, Republic of Korea 2. Electrical Engineering Department, Faculty of Engineering, Assiut University, Assiut 71515, Egypt
Abstract
Due to its widespread usage in many applications, numerous deep learning algorithms have been proposed to overcome Light Field’s trade-off (LF). The sensor’s low resolution limits angular and spatial resolution, which causes this trade-off. The proposed method should be able to model the non-local properties of the 4D LF data fully to mitigate this problem. Therefore, this paper proposes a different approach to increase spatial and angular information interaction for LF image super-resolution (SR). We achieved this by processing the LF Sub-Aperture Images (SAI) independently to extract the spatial information and the LF Macro-Pixel Image (MPI) to extract the angular information. The MPI or Lenslet LF image is characterized by its ability to integrate more complementary information between different viewpoints (SAIs). In particular, we extract initial features and then process MAI and SAIs alternately to incorporate angular and spatial information. Finally, the interacted features are added to the initial extracted features to reconstruct the final output. We trained the proposed network to minimize the sum of absolute errors between low-resolution (LR) input and high-resolution (HR) output images. Experimental results prove the high performance of our proposed method over the state-of-the-art methods on LFSR for small baseline LF images.
Funder
National Research Foundation of Korea
Subject
Electrical and Electronic Engineering,Biochemistry,Instrumentation,Atomic and Molecular Physics, and Optics,Analytical Chemistry
Reference40 articles.
1. Light field image processing: An overview;Wu;IEEE J. Sel. Top. Signal Process.,2017 2. Wang, Y., Wang, L., Liang, Z., Yang, J., An, W., and Guo, Y. (2022, January 19–20). Occlusion-Aware Cost Constructor for Light Field Depth Estimation. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, New Orleans, LA, USA. 3. Gao, M., Deng, H., Xiang, S., Wu, J., and He, Z. (2022). EPI Light Field Depth Estimation Based on a Directional Relationship Model and Multiviewpoint Attention Mechanism. Sensors, 22. 4. Li, Y., Yang, W., Xu, Z., Chen, Z., Shi, Z., Zhang, Y., and Huang, L. (2021, January 6–11). Mask4D: 4D convolution network for light field occlusion removal. Proceedings of the ICASSP 2021—2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Toronto, ON, Canada. 5. Wang, Y., Wu, T., Yang, J., Wang, L., An, W., and Guo, Y. (2020, January 1–5). DeOccNet: Learning to see through foreground occlusions in light fields. Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, Snowmass Village, CO, USA.
|
|