Increasing Video Detail Using Super-Resolution?

Cecil Esquivel asks: "I'm looking for ways to increase the quality of video by using super-resolution algorithms which use the visual information across multiple frames of video to increase the resolution of individual frames. I have found very little on the web that can do this effectively for the entire length of video. There is commercial software, VideoFOCUS, which produces hi-res stills from video, but doesn't seem to have a product for producing hi-res video from video. There is a thesis from Duke U. which is 6 years old, monochrome only and is mostly proof of concept.) Anybody out there have more information or is willing to help me develop some software that can do this? Darwin/Mac OS X solution that can work with QuickTime DV, preferred." Typically, super-resolution uses image samples generated from low-resolution and high-resolution samples of the same source, which is then converted into source independent information that can be used to increase detail for other low resolution sources. Has anyone seen programs that use super-resolution techniques for increasing the resolution of your typical digital video clip?

Spatial vs. Temporal

[Wavy]

I imagine increasing the spatial resolution for a frame of footage decreases the temporal resolution of the set of frames. My gut feeling is that you would see more after/pre-image than in the source.

Surely this should be evident

[Anonymous Coward]

There is commercial software, VideoFOCUS, which produces hi-res stills from video, but doesn't seem to have a product for producing hi-res video from video.

You can't figure out why that is?

Found some more information

[MoOsEb0y]

Ok, after googling for a little bit (I will never MSN anything!), I found a site who has done just what you were describing with MPEG video.

http://www.ai.mit.edu/~brussell/research/sres/data / [mit.edu]

Anyways, it seems that without proper filtering, the output looks REALLY weird. (look at they guy walking in a circle in front of the quilt) It seems that the motion vectors from the MPEG get taken in as part of the detected edges somehow! Thus, this would be most useful for uncompressed analog video as an input.

Re:Oh yea. I've seen this.

[hawkstone]

I realize the root was probably a troll (the AC, not you). Also, the submitter was technically asking about nearby frames. Realizing that, however, I'll respond anyway, because I feel the technique is at least worth a mention:

There is nevertheless a form of super-resolution which works on standalone single frames. It depends on what you mean by "additional detail". Normally when magnifying images you would use nearest-neighbor, or better yet, bilinear interpolation. But a magnification using these methods will still look blocky.

Now suppose you first detect the edges in your lo-res image. When you magnify, use that information to determine which pieces of the newly created pixels should be colored what. You can use a similar concept for textured areas without edges. The result? Through some simple assumptions, you get much better magnification than through other schemes.

If a star in your original image is a 5-pixel plus pattern, a super-resolution image might turn it into a circle. Though not strictly accurate, this is in fact not a bad result in many situations. However, you're right that there is really no more detail; if a star was not visible in the original image, it never will be.

This isn't much help, but....

[nzyank]

When I worked at HP (R&D) we had some pretty cool stuff for doing very similar things. Most of it came from Purdue or Palo Alto and then we made it actually work. All patented as fast as we got them working and sometimes sooner. Betcha you're going to run into that in real life. Even if you think of something 'novel' the patent's probably already filed or granted for what you're wanting to do.