首页> 外文会议>IEEE International Conference on Image Processing >Enhancing Quality for VVC Compressed Videos by Jointly Exploiting Spatial Details and Temporal Structure
【24h】

Enhancing Quality for VVC Compressed Videos by Jointly Exploiting Spatial Details and Temporal Structure

机译:通过联合利用空间细节和时间结构来提高VVC压缩视频的质量

获取原文

摘要

In this paper, we propose a quality enhancement network of versatile video coding (VVC) compressed videos by jointly exploiting spatial details and temporal structure (SDTS). The proposed network consists of a temporal structure fusion subnet and a spatial detail enhancement subnet. The former subnet is used to estimate and compensate the temporal motion across frames, and the latter subnet is used to reduce the compression artifacts and enhance the reconstruction quality of compressed video. Experimental results demonstrate the effectiveness of our SDTS-based method. The code of our proposed method is available at https://github.com/mengab/SDTS
机译:在本文中,我们通过共同利用空间细节和时间结构(SDTS),提出了一种通用视频编码(VVC)压缩视频的质量增强网络。所提出的网络由时间结构融合子网和空间细节增强子网组成。前一个子网用于估计和补偿跨帧的时间运动,后一个子网用于减少压缩伪像并提高压缩视频的重建质量。实验结果证明了我们基于SDTS的方法的有效性。我们提议的方法的代码可从https://github.com/mengab/SDTS获得。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号