论文标题
通过基于CNN的邮政处理的视频压缩
Video Compression with CNN-based Post Processing
论文作者
论文摘要
近年来，由于与高质量和身临其境的视频内容相关的迅速增加的需求，视频压缩技术受到了重大挑战。在各种压缩工具中，可以将后处理应用于重建的视频内容，以减轻可见的压缩工件并提高整体感知质量。受深度学习进步的启发，我们提出了一种新的基于CNN的后处理方法，该方法已与两个最先进的编码标准VVC和AV1集成。结果表明，在各种空间分辨率下，所有测试序列的编码增长一致，对原始VVC和AV1的平均比特率分别节省了4.0％和5.8％（根据PSNR的评估）。该网络还接受了感知启发的损失功能的培训，基于感知质量评估（VMAF）进一步提高了重建质量，平均编码比VVC的平均编码增长率为13.9％，对AV1的编码增长了10.5％。
In recent years, video compression techniques have been significantly challenged by the rapidly increased demands associated with high quality and immersive video content. Among various compression tools, post-processing can be applied on reconstructed video content to mitigate visible compression artefacts and to enhance overall perceptual quality. Inspired by advances in deep learning, we propose a new CNN-based post-processing approach, which has been integrated with two state-of-the-art coding standards, VVC and AV1. The results show consistent coding gains on all tested sequences at various spatial resolutions, with average bit rate savings of 4.0% and 5.8% against original VVC and AV1 respectively (based on the assessment of PSNR). This network has also been trained with perceptually inspired loss functions, which have further improved reconstruction quality based on perceptual quality assessment (VMAF), with average coding gains of 13.9% over VVC and 10.5% against AV1.
