TL;DR本研究提出 DynaVSR 框架,采用元学习技术,在实际视频 SR 场景下实现了较快速的降采样模型估计和自适应学习,并与视频 SR 网络无缝结合,实现了比现有的盲目 SR 方法更快的推理时间和更高的性能提升。
Abstract
Most conventional supervised super-resolution (SR) algorithms assume that
low-resolution (LR) data is obtained by downscaling high-resolution (HR) data
with a fixed known kernel, but such an assumption often does not hold in real
scenarios. Some recent blind SR algorithms have been pro