Video epitome super resolution

An optical zoom in modern cameras allows the user to trade the field of view for the level of captured detail. The user often desires to capture both the large context of the scene and the detail in it, by first capturing a wide angle shot followed by a large zoom (as shown in the following video) and slow scene scanning at the constant zoom level (omitted in the set-up video for brevity). The video epitome learnt on the high-resolution "scene scanning video" captured at the higher zoom level can be used to super-resolve the original wide-angle shot.

In the demo provided, the wide shot captures a large plant moving in the wind. Later, the camera zooms in and scans the plant creating the shot used for training the high resolution epitome. The high resolution textural and shape features of the plant, as well as the motion patterns, are then used to compute a super-resolved version of the wide shot. Note that the content of the wide shot is similar, but far from identical to the content of the high resolution training data.

Vincent Cheung, Brendan J. Frey, and Nebojsa Jojic, "Video Epitomes", In Proc. IEEE CVPR 2005.

Vincent Cheung

Category:

Education

Tags:

• googlevideo

[TheKeddie]

Hey! pliz explain me this video epitome concept for super resolution! i m unable to comprehend it, although i have its matlab code, it's too difficult to make out from it, coud u pliz explain me abt it in brief

Thx in advance!