⚡ 本页包含 AI 生成的分析内容,仅供参考
本文提出了一款用于4K超高清真视频超分辨率的图像信号处理器,实现了210fps的高帧率处理。该处理器采用基于神经网络的框架,包含对齐和细化阶段,旨在将低分辨率视频转换为高分辨率视频,适用于流媒体和视频会议等低带宽场景。
Google, Mountain View, CA 1 2 Video super-resolution (VSR) aims to convert low-resolution (LR) videos to high-resolution (HR) videos with high image quality [1]. It can be used for various video applications, such as streaming and conferencing, given low-bandwidth connectivity. Figure 2.8.1 shows a neural network (NN)-based VSR framework that comprises alignment and refinement stages
Ying-Sheng Lin1, Jun Nishimura2, Chia-Hsiang Yang1
National Taiwan University, Taipei, Taiwan