Suppose you have a cherished home video, taken at your birthday party. You're fond of the video, but your viewing experience is marred by one small, troubling detail. There in the video, framed and hanging on the living room wall amidst the celebration, is a color photograph of your former significant other.
Solution
But what if you could somehow reach inside the video and swap the offending photo for a snapshot of your current love? How perfect would that be?
A group of Stanford University researchers specializing in artificial intelligence have developed software that makes such a switch relatively simple. The researchers, computer science graduate students Ashutosh Saxena and Siddharth Batra, and Assistant Professor Andrew Ng, see interesting potential for the technology they call ZunaVision.
Video courtesy Stanford News Service
© Stanford University. All Rights Reserved.
They say a user of the software can easily plunk an image on almost any planar surface in a video, whether wall, floor or ceiling. And the embedded images don't have to be still photos - you can insert a video inside a video.
Here's the opportunity to sing karaoke side-by-side with your favorite American Idol celebrity and post the video to YouTube. Or preview a virtual copy of a painting on your wall before you buy. Or liven up those dull vacation videos.
There is also a potential financial aspect to the technology. The researchers suggest that anyone with a video camera might earn some spending money by agreeing to have unobtrusive corporate logos placed inside their videos before they are posted online. The person who shot the video, and the company handling the business arrangements, would be paid per view, in a fashion analogous to Google AdSense, which pays websites to run small ads.
Source [Stanford News Service]
© Stanford University. All Rights Reserved.
Solution
But what if you could somehow reach inside the video and swap the offending photo for a snapshot of your current love? How perfect would that be?
A group of Stanford University researchers specializing in artificial intelligence have developed software that makes such a switch relatively simple. The researchers, computer science graduate students Ashutosh Saxena and Siddharth Batra, and Assistant Professor Andrew Ng, see interesting potential for the technology they call ZunaVision.
Video courtesy Stanford News Service
© Stanford University. All Rights Reserved.
They say a user of the software can easily plunk an image on almost any planar surface in a video, whether wall, floor or ceiling. And the embedded images don't have to be still photos - you can insert a video inside a video.
Here's the opportunity to sing karaoke side-by-side with your favorite American Idol celebrity and post the video to YouTube. Or preview a virtual copy of a painting on your wall before you buy. Or liven up those dull vacation videos.
There is also a potential financial aspect to the technology. The researchers suggest that anyone with a video camera might earn some spending money by agreeing to have unobtrusive corporate logos placed inside their videos before they are posted online. The person who shot the video, and the company handling the business arrangements, would be paid per view, in a fashion analogous to Google AdSense, which pays websites to run small ads.
Source [Stanford News Service]
© Stanford University. All Rights Reserved.
No comments:
Post a Comment