Inpainting of Vintage Films Based on Variational Auto-encoder

摘要

There are many existing video restoration frameworks, but there are no professional methods to deal with multiple degradation restorations of vintage films. With the help of the idea of mapping, this paper constructs a model with two variational autoencoders to repair the complex degradation problem. In addition, convolutional LSTM is used for video de-flicker processing to obtain smoother and natural results. The experimental results prove that this method can repair different damages in the vintage films screen at the same time, and achieve good results.