🐢University of Maryland, College Park Adobe Research 8× Upsampling results (128×128→1024×1024) Our model is able to upsample a video up to 8× with rich details. Abstract Video super-resolution (VSR) approaches have shown impressive temporal consistency in upsampled videos. However, these approaches tend to generate blurrier results than their image counterparts as they are limited in their generative capability. This raises a fundamental question: can we extend the success of a generative image...