Disentangling light fields for super-resolution and disparity estimation

Y Wang, L Wang, G Wu, J Yang, W An… - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
Light field (LF) cameras record both intensity and directions of light rays, and encode 3D
scenes into 4D LF images. Recently, many convolutional neural networks (CNNs) have …

Learning non-local spatial-angular correlation for light field image super-resolution

Z Liang, Y Wang, L Wang, J Yang… - Proceedings of the …, 2023 - openaccess.thecvf.com
Exploiting spatial-angular correlation is crucial to light field (LF) image super-resolution
(SR), but is highly challenging due to its non-local property caused by the disparities among …

Cross-view recurrence-based self-supervised super-resolution of light field

H Sheng, S Wang, D Yang, R Cong… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
Compared with external-supervised learning-based (ESLB) methods, self-supervised
learning-based (SSLB) methods can overcome the domain gap problem caused by different …

[HTML][HTML] A survey for light field super-resolution

M Zhao, H Sheng, D Yang, S Wang, R Cong… - High-Confidence …, 2024 - Elsevier
Compared to 2D imaging data, the 4D light field (LF) data retains richer scene's structure
information, which can significantly improve the computer's perception capability, including …