Switchable Cnn-Based Same-Resolution and Super-Resolution in-Loop Restoration For Next Generation Video Codecs

We propose a novel rendering method for computer-generated holograms (CGHs) which enables low memory usage and low computational complexity. Although the conventional elementary hologram (EH) method realizes smooth motion parallax and rendering for realistic expressions with low complexity, it incurs large memory usage. This is because point light sources (PLSs) must be acquired and stored independently for different perspectives to reconstruct multiview images. Our method effectively reduces memory usage by integrating PLSs whose 3D coordinates are extremely close to each other. Furthermore, to reduce the complexity of this integration, our method skips some of the PLS acquisition processes under the assumption that the loss of PLSs for the EH does not significantly affect the final reconstructed image quality. Our experimental results show a reduction in memory usage of 93% with a calculation time only 1.2-fold longer than compared with the EH method.