“…For comparing enhancement performance on sRGB images, we choose publicly available supervised-learning-based algorithms such as DALE [28], DLN [61], DSLR [32], Enlight-enGAN [20], GLAD [63], MBLLEN [41], KinD [79], RetinexNet [67] and URIE [57], whereas for RAW images, we choose Rawpy 1 , RAW2RGB-GAN [82], TENet [46], PyNet [17], ELD [68], AWNet [12]. We summarize the qualitative performance on LOL and SID-Sony datasets along with computational requirement in GMAC (Giga-Multiplication and Accumulation Operations) 2 3 in Tab.…”