Each image was converted to YCrCb format, and only the luminance channel (Y) was used. This model can be extended to use the other channels as well. Extract sub-images: From the 91 images, sub-images ...

Abstract: The rapid development of deep learning has driven the breakthrough in performance of single image super-resolution (SISR). However, many existing works deepen the network to pursue ...

Abstract: Light-Field (LF) image is emerging 4D data of light rays that is capable of realistically presenting spatial and angular information of 3D scene. However, the large data volume of LF images ...

LFIC-DRASC is a deep learning model for light field image compression, which maintains spatial consistency through a special network structure, improving compression efficiency and visual quality.