Enhancing Quality for VVC Compressed Videos with Omniscient Quality Enhancement Model

TL;DR

The paper addresses the challenge of maintaining high perceptual quality in VVC (H.266) video by extending the Omniscient Video Quality Enhancement (OVQE) framework to VVC (OVQE_VVC). The approach leverages omni-frequency and spatiotemporal information within an end-to-end learning model integrated at the VVC decoder, achieving $0.74$–$1.2$ dB PSNR gains and about $19.6\%$ bitrate savings, with BD-Rate improvements up to $-29.69\%$ over STD_VVC. Experimental results on 13 CTC sequences demonstrate that OVQE_VVC outperforms relevant QE baselines like MFQE 2.0 and STDF. The work signifies a practical path to enhancing decoded video quality and compression efficiency for modern codecs, and points to further multi-rate OVQE optimizations as future work.

Abstract

The latest video coding standard H.266/VVC has shown its great improvement in terms of compression performance when compared to its predecessor HEVC standard. Though VVC was implemented with many advanced techniques, it still met the same challenges as its predecessor due to the need for even higher perceptual quality demand at the decoder side as well as the compression performance at the encoder side. The advancement of Artificial Intelligence (AI) technology, notably the deep learning-based video quality enhancement methods, was shown to be a promising approach to improving the perceptual quality experience. In this paper, we propose a novel Omniscient video quality enhancement Network for VVC compressed Videos. The Omniscient Network for compressed video quality enhancement was originally designed for HEVC compressed videos in which not only the spatial-temporal features but also cross-frequencies information were employed to augment the visual quality. Inspired by this work, we propose a modification of the OVQE model and integrate it into the lasted STD-VVC (Standard Versatile Video Coding) decoder architecture. As assessed in a rich set of test conditions, the proposed OVQE-VVC solution is able to achieve significant PSNR improvement, notably around 0.74 dB and up to 1.2 dB with respect to the original STD-VVC codec. This also corresponds to around 19.6% of bitrate saving while keeping a similar quality observation.

Figures (4)

• Figure 1: Loss of high-frequency information due to compression peng2022ovqe.
• Figure 2: First frame of test video sequences.
• Figure 3: PSNR curves of VVC baseline and proposed OVQE_VVC approach.
• Figure 4: RD comparison.