Comments on: Fixing Video with Photographs http://www.techcrunch.com/2008/08/15/fixing-video-with-photographs/ Startup and Technology News Thu, 26 Nov 2009 13:24:56 -0800 hourly 1 By: Video Links http://www.techcrunch.com/2008/08/15/fixing-video-with-photographs/comment-page-1/#comment-2439760 Video Links Mon, 18 Aug 2008 08:47:08 +0000 http://www.techcrunch.com/?p=21129#comment-2439760 Does it use Fuzzy Logic, ha-har-har :) http://www.acomputerportal.com/videos_to_watch_video_publishing.html Does it use Fuzzy Logic, ha-har-har :)

http://www.acom...publishing.html

]]> By: coke http://www.techcrunch.com/2008/08/15/fixing-video-with-photographs/comment-page-1/#comment-2439739 coke Mon, 18 Aug 2008 08:11:40 +0000 http://www.techcrunch.com/?p=21129#comment-2439739 Isn't something like that most video compression algorithms do to reduce the size of a movie? Put a keyframe and then "guess" the upcoming part of the video using only that for some of the changes on the image? Isn’t something like that most video compression algorithms do to reduce the size of a movie? Put a keyframe and then “guess” the upcoming part of the video using only that for some of the changes on the image?

]]> By: KOPN Tech Radio » Blog Archive » News Bytes for 8/18/2008 http://www.techcrunch.com/2008/08/15/fixing-video-with-photographs/comment-page-1/#comment-2439649 KOPN Tech Radio » Blog Archive » News Bytes for 8/18/2008 Mon, 18 Aug 2008 05:44:02 +0000 http://www.techcrunch.com/?p=21129#comment-2439649 [...] From Siggraph ‘08 — fixing video using photos [...] [...] From Siggraph ‘08 — fixing video using photos [...]

]]> By: W http://www.techcrunch.com/2008/08/15/fixing-video-with-photographs/comment-page-1/#comment-2439363 W Sun, 17 Aug 2008 19:32:55 +0000 http://www.techcrunch.com/?p=21129#comment-2439363 It doesn't seem to solve world peace. Still waiting for that. It doesn’t seem to solve world peace. Still waiting for that.

]]> By: TechCrunch Japanese アーカイブ » スチル写真でビデオの画質を大幅改善する技術 http://www.techcrunch.com/2008/08/15/fixing-video-with-photographs/comment-page-1/#comment-2439081 TechCrunch Japanese アーカイブ » スチル写真でビデオの画質を大幅改善する技術 Sun, 17 Aug 2008 07:30:59 +0000 http://www.techcrunch.com/?p=21129#comment-2439081 [...] [原文へ] [...] [...] [原文へ] [...]

]]> By: T3chlusive http://www.techcrunch.com/2008/08/15/fixing-video-with-photographs/comment-page-1/#comment-2438833 T3chlusive Sat, 16 Aug 2008 23:34:36 +0000 http://www.techcrunch.com/?p=21129#comment-2438833 I wonder if it's automated. I don't see how they could remove an artifact like a street sign from the middle of the photo with automation ?? I wonder if it’s automated. I don’t see how they could remove an artifact like a street sign from the middle of the photo with automation ??

]]> By: Salik Syed http://www.techcrunch.com/2008/08/15/fixing-video-with-photographs/comment-page-1/#comment-2438794 Salik Syed Sat, 16 Aug 2008 20:43:45 +0000 http://www.techcrunch.com/?p=21129#comment-2438794 Have you ever heard of lightfields? If not you might want to read the wikipedia article... In the most basic sense... they fill in pixels that are occluded with information created from a light field. This light field is generated by computing the camera position based on the estimated scene geometry. This will only work well if the background is not really moving relative to the camera... if those flowers were swaying it wouldn't be able to fill in the missing pixels as most of the information in the light field would be very noisy and inaccurate (since the depth map is really really low res i doubt the generated light field would be accurate at all) Have you ever heard of lightfields? If not you might want to read the wikipedia article… In the most basic sense… they fill in pixels that are occluded with information created from a light field. This light field is generated by computing the camera position based on the estimated scene geometry.
This will only work well if the background is not really moving relative to the camera… if those flowers were swaying it wouldn’t be able to fill in the missing pixels as most of the information in the light field would be very noisy and inaccurate (since the depth map is really really low res i doubt the generated light field would be accurate at all)

]]> By: emma http://www.techcrunch.com/2008/08/15/fixing-video-with-photographs/comment-page-1/#comment-2438660 emma Sat, 16 Aug 2008 12:38:48 +0000 http://www.techcrunch.com/?p=21129#comment-2438660 how about exposing the damn shot properly and shooting in hi def? technology is search of a problem and motion match has been around for years! how about exposing the damn shot properly and shooting in hi def?

technology is search of a problem and motion match has been around for years!

]]> By: Markus http://www.techcrunch.com/2008/08/15/fixing-video-with-photographs/comment-page-1/#comment-2438614 Markus Sat, 16 Aug 2008 09:20:44 +0000 http://www.techcrunch.com/?p=21129#comment-2438614 I think (but I'm not positive) that the photos must be taken at the same time as the video. If you think about it, a scene at a different time of day/year would have entirely different lighting and shadows (not to mention all the other things in the photo that could change over time). On the other hand, since Photosynth can piece together photos from different times and angles maybe it is indeed possible. It would be very cool. I think (but I’m not positive) that the photos must be taken at the same time as the video.

If you think about it, a scene at a different time of day/year would have entirely different lighting and shadows (not to mention all the other things in the photo that could change over time).

On the other hand, since Photosynth can piece together photos from different times and angles maybe it is indeed possible. It would be very cool.

]]> By: Markus http://www.techcrunch.com/2008/08/15/fixing-video-with-photographs/comment-page-1/#comment-2438613 Markus Sat, 16 Aug 2008 09:15:12 +0000 http://www.techcrunch.com/?p=21129#comment-2438613 No. American viewers are watching the Olympics via NBC using Silverlight. America is *not* the whole world. At least not yet :-/ No. American viewers are watching the Olympics via NBC using Silverlight.

America is *not* the whole world.

At least not yet :-/

]]> By: G http://www.techcrunch.com/2008/08/15/fixing-video-with-photographs/comment-page-1/#comment-2438569 G Sat, 16 Aug 2008 06:51:24 +0000 http://www.techcrunch.com/?p=21129#comment-2438569 it sure has! The whole world is watching Olympics online LIVE using NBC-Microsoft partnership of using SilverLight. it sure has! The whole world is watching Olympics online LIVE using NBC-Microsoft partnership of using SilverLight.

]]> By: ybbet http://www.techcrunch.com/2008/08/15/fixing-video-with-photographs/comment-page-1/#comment-2438559 ybbet Sat, 16 Aug 2008 06:31:16 +0000 http://www.techcrunch.com/?p=21129#comment-2438559 These people have created the need for a Nobel Prize in Pure Magic. This stuff is awesome! These people have created the need for a Nobel Prize in Pure Magic. This stuff is awesome!

]]> By: green jaded http://www.techcrunch.com/2008/08/15/fixing-video-with-photographs/comment-page-1/#comment-2438551 green jaded Sat, 16 Aug 2008 06:09:41 +0000 http://www.techcrunch.com/?p=21129#comment-2438551 I can't imagine going back to shoot photos of some static object just to fix up old video. If it worked with Photosynth so you could autoscan Flickr for helpful photos that would be awesome. Otherwise you might as well just reshoot the video with a better camera. I can’t imagine going back to shoot photos of some static object just to fix up old video. If it worked with Photosynth so you could autoscan Flickr for helpful photos that would be awesome. Otherwise you might as well just reshoot the video with a better camera.

]]> By: chris walker http://www.techcrunch.com/2008/08/15/fixing-video-with-photographs/comment-page-1/#comment-2438545 chris walker Sat, 16 Aug 2008 05:43:34 +0000 http://www.techcrunch.com/?p=21129#comment-2438545 hehe - like Silverlight will ever really take off! hehe – like Silverlight will ever really take off!

]]> By: tm http://www.techcrunch.com/2008/08/15/fixing-video-with-photographs/comment-page-1/#comment-2438517 tm Sat, 16 Aug 2008 03:40:55 +0000 http://www.techcrunch.com/?p=21129#comment-2438517 Most of the time I see stuff on TechCrunch which is not commonly known in the industry, mostly insider news. This work was done in early 2007 and it is available on Youtube since that time. The paper was also published in 2007. Very late on TC. There must be intellectual property ownership issues because co-authors are from Microsfot Research, Adobe, Berkeley and Washingtom.. Microsoft and Adobe already have too much to fight for... Silverlight vs Flash... Most of the time I see stuff on TechCrunch which is not commonly known in the industry, mostly insider news.

This work was done in early 2007 and it is available on Youtube since that time. The paper was also published in 2007. Very late on TC.

There must be intellectual property ownership issues because co-authors are from Microsfot Research, Adobe, Berkeley and Washingtom.. Microsoft and Adobe already have too much to fight for… Silverlight vs Flash…

]]> By: tony http://www.techcrunch.com/2008/08/15/fixing-video-with-photographs/comment-page-1/#comment-2438468 tony Sat, 16 Aug 2008 01:37:19 +0000 http://www.techcrunch.com/?p=21129#comment-2438468 artifacts are things like noise, flares, sensor dust. artifacts is NOT overexposure nor low resolution. artifacts are things like noise, flares, sensor dust.

artifacts is NOT overexposure nor low resolution.

]]> By: Yakubovich http://www.techcrunch.com/2008/08/15/fixing-video-with-photographs/comment-page-1/#comment-2438466 Yakubovich Sat, 16 Aug 2008 01:36:44 +0000 http://www.techcrunch.com/?p=21129#comment-2438466 While this looks amazing, you have to keep in mind that they must have had a grad student spending hours or weeks tweaking the results. There are components in their algorithms that would be considered major breakthroughs if they could be automated effectively. For example, there is a point where they "automatically" get a depth map from a static image. On the other hand, if these cameras become mainstream, it could work: http://www.crunchgear.com/2008/03/20/12616-lens-camera-to-take-infinite-depth-of-field-pictures/ While this looks amazing, you have to keep in mind that they must have had a grad student spending hours or weeks tweaking the results. There are components in their algorithms that would be considered major breakthroughs if they could be automated effectively. For example, there is a point where they “automatically” get a depth map from a static image.

On the other hand, if these cameras become mainstream, it could work: http://www.crun...field-pictures/

]]> By: Thomas http://www.techcrunch.com/2008/08/15/fixing-video-with-photographs/comment-page-1/#comment-2438465 Thomas Sat, 16 Aug 2008 01:32:21 +0000 http://www.techcrunch.com/?p=21129#comment-2438465 The sample with the flower looks like a fake. How do they recreate the background behind the parking sign ? I'm a little suspicious on that one. Hard to believe for me. The sample with the flower looks like a fake. How do they recreate the background behind the parking sign ? I’m a little suspicious on that one. Hard to believe for me.

]]> By: chris http://www.techcrunch.com/2008/08/15/fixing-video-with-photographs/comment-page-1/#comment-2438456 chris Sat, 16 Aug 2008 01:20:24 +0000 http://www.techcrunch.com/?p=21129#comment-2438456 Impressive - but when can I get my hands on a FCP plugin? Impressive – but when can I get my hands on a FCP plugin?

]]> By: mp http://www.techcrunch.com/2008/08/15/fixing-video-with-photographs/comment-page-1/#comment-2438455 mp Sat, 16 Aug 2008 01:20:22 +0000 http://www.techcrunch.com/?p=21129#comment-2438455 John, low resolution has nothing to do with the person behind the camera, but is rather a function of the camera. Over exposure on the other hand is simply that... it can lead to artifacts, but it doesn't necessarily have to! - mp John,
low resolution has nothing to do with the person behind the camera, but is rather a function of the camera. Over exposure on the other hand is simply that… it can lead to artifacts, but it doesn’t necessarily have to!

– mp

]]> By: Mitchell Joyce http://www.techcrunch.com/2008/08/15/fixing-video-with-photographs/comment-page-1/#comment-2438451 Mitchell Joyce Sat, 16 Aug 2008 01:11:12 +0000 http://www.techcrunch.com/?p=21129#comment-2438451 I enjoy things that are automatically automatic, I find it joyful. I enjoy things that are automatically automatic, I find it joyful.

]]> By: John Biggs http://www.techcrunch.com/2008/08/15/fixing-video-with-photographs/comment-page-1/#comment-2438436 John Biggs Sat, 16 Aug 2008 00:51:08 +0000 http://www.techcrunch.com/?p=21129#comment-2438436 They are artifacts of a poor videographer just as pixelation et al are artifacts of poor compression. They are artifacts of a poor videographer just as pixelation et al are artifacts of poor compression.

]]> By: Ian http://www.techcrunch.com/2008/08/15/fixing-video-with-photographs/comment-page-1/#comment-2438429 Ian Sat, 16 Aug 2008 00:39:17 +0000 http://www.techcrunch.com/?p=21129#comment-2438429 this is the coolest thing i've seen since photosynth this is the coolest thing i’ve seen since photosynth

]]> By: mp http://www.techcrunch.com/2008/08/15/fixing-video-with-photographs/comment-page-1/#comment-2438428 mp Sat, 16 Aug 2008 00:32:01 +0000 http://www.techcrunch.com/?p=21129#comment-2438428 "Video might contain artifacts like overexposure and low-resolution imagery" Overexposure and low-resolution are not artifacts. “Video might contain artifacts like overexposure and low-resolution imagery”

Overexposure and low-resolution are not artifacts.

]]> By: frank http://www.techcrunch.com/2008/08/15/fixing-video-with-photographs/comment-page-1/#comment-2438418 frank Sat, 16 Aug 2008 00:15:42 +0000 http://www.techcrunch.com/?p=21129#comment-2438418 i like to automatically improve things automatically as well. i like to automatically improve things automatically as well.

]]>