Deformable Convolution Dense Network for Compressed Video Quality Enhancement

Different from the traditional video quality enhancement, the goal of compressed video quality enhancement is to reduce the artifacts brought by the video compression. The existing multi-frame methods for compressed video quality enhancement heavily rely on optical flow, which is both inefficient and limited in performance. In this paper, a Multi-frame Residual Dense Network (MRDN) with deformable convolution is developed to improve the quality of the compressed video, by utilizing high-quality frame to compensate the low-quality frame. Specifically, the proposed network consists of the developed Motion Compensation (MC) module and Quality Enhancement (QE) module, aiming to compensate and enhance the quality of the input frame, respectively. Besides, a novel edge enhancement loss is conducted on the enhanced frame, in order to enhance edge structure during the training. Finally, the experimental results over a public benchmark show that our method outperforms the state-of-the-art methods for compressed video quality enhancement.