“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. Additionally, the user can quickly modify the video by editing only a few still images of the scene. Finally, our system allows a user to remove unwanted objects and camera shake from the video.”

Pravin Bhat, C. Lawrence Zitnick, Noah Snavely, Aseem Agarwala, Maneesh Agrawala, Brian Curless, Michael Cohen and Sing Bing Kang are brilliant!

Basically, this is a system for automatically enhancing a video and adding visual effects.

But unlike traditional visual effects software (After Effects, Shake, Boujou, etc), the system is completely automatic and no intervention is required from the user.

There is one (major) limitation at this stage… it can handle only videos of static scenes (i.e., videos shot with a moving camera but containing no moving objects in the scene).

I’m sure they will be able to solve this problem in the future tho.