PeQuENet: Perceptual Quality Enhancement of Compressed Video with Adaptation- and Attention-based Network. (arXiv:2206.07893v1 [cs.CV])

Web: http://arxiv.org/abs/2206.07893

In this paper we propose a generative adversarial network (GAN) framework to
enhance the perceptual quality of compressed videos. Our framework includes
attention and adaptation to different quantization parameters (QPs) in a single
model. The attention module exploits global receptive fields that can capture
and align long-range correlations between consecutive frames, which can be
beneficial for enhancing perceptual quality of videos. The frame to be enhanced
is fed into the deep network together with its neighboring frames, and in the …

arxiv attention cv network video