Abstract
With the rapid advancement in many multimedia applications, such as video gaming, computer vision applications, and video streaming and surveillance, video quality remains an open challenge. Despite the existence of the standardized video quality as well as high definition (HD) and ultrahigh definition (UHD), enhancing the quality for the video compression standard will improve the video streaming resolution and satisfy end user's quality of service (QoS). Versatile video coding (VVC) is the latest video coding standard that achieves significant coding efficiency. VVC will help spread high-quality video services and emerging applications, such as high dynamic range (HDR), high frame rate (HFR), and omnidirectional 360-degree multimedia compared to its predecessor high efficiency video coding (HEVC). Given its valuable results, the emerging field of deep learning is attracting the attention of scientists and prompts them to solve many contributions. In this study, we investigate the deep learning efficiency to the new VVC standard in order to improve video quality. However, in this work, we propose a wide-activated squeeze-and-excitation deep convolutional neural network (WSE-DCNN) technique-based video quality enhancement for VVC. Thus, the VVC conventional in-loop filtering will be replaced by the suggested WSE-DCNN technique that is expected to eliminate the compression artifacts in order to improve visual quality. Numerical results demonstrate the efficacy of the proposed model achieving approximately −2.85%, −8.89%, and −10.05% BD-rate reduction of the luma (Y) and both chroma (U, V) components, respectively, under random access profile.
Highlights
With emerging technologies that have rapidly evolved, multimedia services and video applications have significantly increased. erefore, higher resolution (4K and 8K), especially for video games, e-learning, video conferencing, and surveillance tasks, is required to meet end-users viewing quality specifications
We propose a powerful deep CNN-based filtering technique, called the wide-activated squeeze-and-excitation deep convolutional neural network (WSE-DCNN). e proposed technique provides powerful new loop filtering using typical versatile video coding (VVC) standards (DBF, sample adaptive offset (SAO), and adaptive loop filter (ALF)). e goal is to effectively eliminate compression artifacts and improve the reconstructed video quality and meet the end-users services. e purpose of this article is to propose a WSEDCNN technique-based quality enhancement and to implement the scheme proposed in the VVC standard, which provides coding gains for the random access configuration
Results and Discussion e efficiency of the proposed WSE-DCNN-based in-loop filtering scheme under VVC standards is assessed . en, a comparative performance with the existing approaches is introduced
Summary
With emerging technologies that have rapidly evolved, multimedia services and video applications have significantly increased. erefore, higher resolution (4K and 8K), especially for video games, e-learning, video conferencing, and surveillance tasks, is required to meet end-users viewing quality specifications. VVC achieves a BD-rate savings up to 30% at the same quality as HEVC, which is the best standard adopted to offer an appropriate level of performance for new multimedia services. Erefore, VVC’s quality compressed video and images need to be improved. VVC aims to keep highquality compressed video with additional encoding features, it still inevitably suffers from compression artifacts, which can lead to a decrease in the video quality. In this case, loop filters play a crucial role in video and image quality optimization before they are used for interprediction as reference images. As for HEVC, in order to remove video compression artifacts and improve reconstructed video quality, VVC standard adopts the loop filtering technique, including the deblocking filter (DBF), sample adaptive offset (SAO), and adaptive loop filter (ALF). As for HEVC, in order to remove video compression artifacts and improve reconstructed video quality, VVC standard adopts the loop filtering technique, including the deblocking filter (DBF), sample adaptive offset (SAO), and adaptive loop filter (ALF). e DBF is designed to eliminate artifacts along block borders using discontinuity-
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
