A Deep Learning post-processor with a perceptual loss function for video compression artifact removal

Darren Ramsook, Anil C. Kokaram, Neil Birkbeck, Yeping Su, Balu Adsumilli

Abstract: While video compression is necessary for large scale video streaming services, compression at low bitrate can degrade the original video and negatively affect the end user’s quality of experience. Deep Neural Networks (DNNs) are actively researched with respect to artifact removal, however the loss functions that are typically employed follows a derivation of a pixel-wise L <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">p</sup> norm. In this paper we consider a DNN as a post-processor for video compression artifact removal. The DNN is trained using a composite perceptual loss that combines a traditional L <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">p</sup> norm loss and a VMAF proxy network based on the Video Multimethod Assessment Function (VMAF). Results show an improvement in VMAF score over both the training and testing sets.