Pravin Bhat & friends at the University of Washington have put together a rather eye-popping video that demonstrates Using Photographs to Enhance Videos of a Static Scene. I think you’ll dig it. (The removal of the No Parking sign is especially impressive.) [Via Jeff Tranberry]
The work builds upon research by Adobe’s Aseem Agarwala (who was instrumental in bringing Auto-Blend to Photoshop CS3). Adobe Senior Principal Scientist (and UW prof.) David Salesin is helping facilitate more collaboration between Adobe teams & academia, recruiting full-time hires like Aseem & sponsoring visiting researchers like Hany Farid.
(Note: As always, please don’t take my mentioning of various tech demos as a hint about any specific feature showing up in a particular Adobe product. I just post things that I find interesting & inspiring.)
Previously:
What. *That* is freaking witchcraft.
Yea, the wonderful world of imaging stuff. Thanks for sharing info about the PS creators and their bits. Would be fun to hang around the adobe test kitchen.
Witchcraft you can patent though!
Another jawdropping link John.
Looking forward to seeing that incorporated into PS CS5 Extended. 😉 If it can do that with Lamposts wire removal wil be a doddle
Wondrous. If graphcut is what’s allowing all those nifty stuff we need a new easter egg:
Merlin LIves in graphcut.
[begone]
[Heh–totally! –J.]
That is pretty damn cool. I predict the functionality used to remove the no parking sign will be dubbed the “mother in-law” editing feature. Imagine the possibility of who you could remove from family videos 🙂 Also cutting ex’s out of your old photos will now be much easier to do digitally.
[No comment. 😉 –J.]
Seriously this is really impressive. The blending of digital photography and video technology is a truly fascinating evolution to witness. Thanks for the link to the video!
While genuinely jaw-dropping (I especially liked that parking sign demo), and with obvious commercial possibilities, it’s actually the reverse of what I’ve been waiting for: the ability to create high-quality 2D and 3D stills from video. Think photosynth, except with only one camera. Or photographing an entire moving train using one video camera on a tripod.