Research On Video Restoration Via Single Invertible Video Snapshot

Unlike images,finding the desired video content in a large pool of videos is not easy due to the time cost of loading and watching.Most video streaming and sharing services provide the video preview function for a better browsing experience.In this paper,we aim to generate a video preview from a single image.To this end,we propose two cascaded networks,the Motion Embedding Network and the Motion Expansion Network.The Motion Embedding Network aims to embed the spatio-temporal information into an embedded image,called video snapshot.On the other end,the Motion Expansion Network is proposed to invert the video back from the input video snapshot.To hold the invertibility of motion embedding and expansion during training,we design four tailor-made losses and a motion attention module to make the network focus on the temporal information.In order to enhance the viewing experience,our expansion network involves an interpolation module to produce a longer video preview with a smooth transition.Extensive experiments demonstrate that our method can successfully embed the spatio-temporal information of a video into one “live” image,which can be converted back to a video preview.Quantitative and qualitative evaluations are conducted on a large number of videos to prove the effectiveness of our proposed method.In particular,statistics of Peak signal-to-noise ratio(PSNR)and Structural similarity index(SSIM)on a large number of videos show the proposed method is general,and it can generate a high-quality video from a single image.The contributions of our paper are summarized as follows: 1)We propose a general and innovative method to embed the spatio-temporal information of a video into a video snapshot,which can be inverted back to a long video with smooth motion.2)We present a motion attention module to help the network focus on dynamic regions,which enriches the spatio-temporal representations of the learned features.3)We develop an interpolation network that predicts arbitrary intermediate optical flow between two consecutive frames.It allows generating a longer and smoother video preview.