Research Article
Image Demosaicing Based on Generative Adversarial Network
Figure 11
Comparison of reconstructed images from different demosaicing methods for the 22th image in the Kodak database. (a) Ground truth image; (b) enlarged portion in the green box; (c–l) the results by using Bilinear, TL, HQL, Zhang’s, LDI-NAT, ARI, MLRI, RI-GBTF, and DnCNN methods, as well as the proposed method, respectively; (m–v) the residual images corresponding to (c–l).