K Jin, A Yang, Z Wei, S Guo… - Proceedings of the …, 2023 - openaccess.thecvf.com
Light Field (LF) cameras capture rich information in 4D LF images by recording both intensity and angular directions, making it crucial to learn the inherent spatial-angular …
Y Wang, J Yang, L Wang, X Ying, T Wu… - … on Image Processing, 2020 - ieeexplore.ieee.org
Light field (LF) cameras can record scenes from multiple perspectives, and thus introduce beneficial angular information for image super-resolution (SR). However, it is challenging to …
Light field (LF) images acquired by hand-held devices usually suffer from low spatial resolution as the limited sampling resources have to be shared with the angular dimension …
S Zhang, S Chang, Y Lin - IEEE Transactions on Image …, 2021 - ieeexplore.ieee.org
Light Field (LF) cameras are considered to have many potential applications since angular and spatial information is captured simultaneously. However, the limited spatial 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 …
S Zhang, Y Lin, H Sheng - … of the IEEE/CVF conference on …, 2019 - openaccess.thecvf.com
Light field cameras are considered to have many potential applications since angular and spatial information is captured simultaneously. However, the limited spatial resolution has …
Z Cheng, Z Xiong, D Liu - … on Circuits and Systems for Video …, 2019 - ieeexplore.ieee.org
Light field images taken by plenoptic cameras often have a tradeoff between spatial and angular resolutions. In this paper, we propose a novel spatial super-resolution approach for …
Light field (LF) photography is an emerging paradigm for capturing more immersive representations of the real world. However, arising from the inherent tradeoff between the …
Most current super-resolution methods rely on low and high resolution image pairs to train a network in a fully supervised manner. However, such image pairs are not available in real …