類似於之前的paper調研的論文，本博文主要是對於multi-scale在low-level-vision中的應用做調研
《Down-Scaling with Learned Kernels in Multi-Scale Deep Neural Networks for Non-Uniform Single Image》
論文開篇提到“Multi-scale approach has been used for blind image video deblurring problems to yield excellent performance for both conventional and recent deep-learning-based state-of-the-art methods.”看來在deblur領域multi-scale應用較爲廣泛。那麼對於去模糊的任務，multi scale是有效的，那在其他low-level-vision任務上也應該有效
propose convolutional neural network (CNN)-based down-scale methods for multi-scale deep-learning-based non-uniform single image deblurring.