R Cong, H Sheng, D Yang, Z Cui… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
Global context information is particularly important for comprehensive scene understanding. It helps clarify local confusions and smooth predictions to achieve fine-grained and coherent …
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 …
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 …
Data augmentation (DA) is an efficient strategy for improving the performance of deep neural networks. Recent DA strategies have demonstrated utility in single image super-resolution …
Z Cheng, Y Liu, Z Xiong - IEEE Transactions on Computational …, 2022 - ieeexplore.ieee.org
Spatial-angular separable convolution (SAS-conv) has been widely used for efficient and effective 4D light field (LF) feature embedding in different tasks, which mimics a 4D …
G Liu, H Yue, K Li, J Yang - IEEE Transactions on Broadcasting, 2023 - ieeexplore.ieee.org
The disparity information reflects pixel-wise inter-view correlations among sub-aperture images (SAIs) of a light field (LF) image. Existing CNN-based methods for LF spatial super …
H Huang, H Zeng, J Hou, J Chen… - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
This paper proposes a new full-reference image quality assessment (IQA) model for performing perceptual quality evaluation on light field (LF) images, called the spatial and …
W Xing, J Chen - Proceedings of the 30th ACM International Conference …, 2022 - dl.acm.org
We present MVSPlenOctree, a novel approach that can efficiently reconstruct radiance fields for view synthesis. Unlike previous scene-specific radiance fields reconstruction methods …
Non-local self-similarity has been well exploited in the single image super-resolution task as an effective prior. However, due to the difficulty of modeling the 4D correspondence globally …