“…Such methodology hinges on an intermediate for the final reconstruction. Numerous CNN-based methods have also been applied in an endto-end fashion for image processing and generation problems, such as segmentation [24,42], super-resolution [53,22,14,15,44], denoising [25,49,59,47,48], dehazing and deraining [32,55], enhancement [31,56] etc. In a similar spirit, more advanced deep learning based deblurring models [35,54,27,21,58,40] have been designed, e.g., the coarse-to-fine framework [27], recurrent neural networks [40,58], and adversarial learning [21].…”