Transcoded Video Restoration by Temporal Spatial Auxiliary Network
This addresses a practical issue for video platforms like YouTube and TikTok, where repeated transcoding degrades quality, though it is incremental as it builds on existing compressed video restoration methods.
The paper tackles the problem of restoring videos that have undergone multiple encoding and transcoding steps, which previous methods assumed were only compressed once, by proposing a Temporal Spatial Auxiliary Network (TSAN) that uses self-supervised attention training and multi-frame information, achieving superior performance over prior techniques.
In most video platforms, such as Youtube, and TikTok, the played videos usually have undergone multiple video encodings such as hardware encoding by recording devices, software encoding by video editing apps, and single/multiple video transcoding by video application servers. Previous works in compressed video restoration typically assume the compression artifacts are caused by one-time encoding. Thus, the derived solution usually does not work very well in practice. In this paper, we propose a new method, temporal spatial auxiliary network (TSAN), for transcoded video restoration. Our method considers the unique traits between video encoding and transcoding, and we consider the initial shallow encoded videos as the intermediate labels to assist the network to conduct self-supervised attention training. In addition, we employ adjacent multi-frame information and propose the temporal deformable alignment and pyramidal spatial fusion for transcoded video restoration. The experimental results demonstrate that the performance of the proposed method is superior to that of the previous techniques. The code is available at https://github.com/icecherylXuli/TSAN.