LAUSR

Video compression artifacts are widespread in online videos, which greatly affects the quality of the videos. In recent years, the deep learning-based methods for video compression artifacts reduction have made impressive achievements. However, most of existing methods ignore the rich multi-scale information contained in video frames. In this brief, we propose a new multi-scale inter-communication spatio-temporal network (MSICSTN) for video compression artifacts reduction by fully exploring contextual multi-scale information. MSICSTN is constructed on the basis of the multi-scale feature inter-communication module (MSFICM) and the source feature selection enhancement module (SFSEM). Specifically, the MSFICM adaptively generates respective attention weights using channel statistical information after the inter-communication of different scale features, and recalibrates the input multi-scale features to enhance the multi-scale features. The SFSEM utilizes the statistical information of the shallow features of the target frame to fuse the shallow features with the deep features for better dense pixel predictions. The experimental results on test videos demonstrate that our method outperforms the existing methods.