xxxxx1
09-12-2008, 11:49 AM
http://grail.cs.washington.edu/projects/videoenhancement/videoEnhancement_files/image001.jpg
"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."
(Source) (http://grail.cs.washington.edu/projects/videoenhancement/videoEnhancement.htm)
demo: http://www.vimeo.com/1450114
If you were wondering why you might need more resolution on a sensor, here's a hint of things to come. The SFM methods used here are already being implemented in some high-end shops, but require large compute clusters right now; don't expect it at home for a few years.
"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."
(Source) (http://grail.cs.washington.edu/projects/videoenhancement/videoEnhancement.htm)
demo: http://www.vimeo.com/1450114
If you were wondering why you might need more resolution on a sensor, here's a hint of things to come. The SFM methods used here are already being implemented in some high-end shops, but require large compute clusters right now; don't expect it at home for a few years.