Nice tricks by merging photographs and video
I assume this demo reel of this project in computerized imaging shows the drain, where the next two or three bigger speed bumps and core multiplications will find their way into consumption. The projects website “Using Photographs to Enhance Videos of a Static Scene” describes:
We present a framework for automatically enhancing videos of a static scene using a few photographs of the same scene. For example, our system can transfer photographic qualities such as high resolution, high dynamic range and better lighting from the photographs to the video.
At least you should look at the embedded video presenting the capabilities of this technology.