“…Peter, P. proposed a mask optimization network for data optimization in spatial picture-in-picture, with the improvement that a generator and a corresponding optimization network can be jointly trained, with the effect of accurately reflecting the image, achieving a breakthrough in quality and speed. Kumar, A. et al proposed a new patching approach that can use GAN to focus on each aspect of image features, such as color and shape individually, and was validated in two datasets, achieving competitive performance [12]. Jam, J. et al designed a loss model employing two encoders and proposed a recursive residual transition layer that achieved some technical progress in terms of bias and quality for image repair, which was well generalized on a stationary dataset [13].…”