X

MotionDSP promises better photos and video

A CIA-funded start-up hopes consumers as well as spooks will be interested in technology to improve the quality of photos and videos.

Stephen Shankland Former Principal Writer
Stephen Shankland worked at CNET from 1998 to 2024 and wrote about processors, digital photography, AI, quantum computing, computer science, materials science, supercomputers, drones, browsers, 3D printing, USB, and new computing technology in general. He has a soft spot in his heart for standards groups and I/O interfaces. His first big scoop was about radioactive cat poop.
Expertise Processors, semiconductors, web browsers, quantum computing, supercomputers, AI, 3D printing, drones, computer science, physics, programming, materials science, USB, UWB, Android, digital photography, science. Credentials
  • Shankland covered the tech industry for more than 25 years and was a science writer for five years before that. He has deep expertise in microprocessors, digital photography, computer hardware and software, internet standards, web technology, and more.
Stephen Shankland
3 min read

I'm among the legions who fume when the investigator on the TV show zooms in endlessly on a photo to uncover some minute detail that in reality couldn't have been photographed by any camera. Worst is when the investigator clicks some "increase resolution" button to smooth a bunch of blocky pixels into a richly detailed image.

This low-resolution image shows the greater detail that can be shown in the license plate by combining data from several frames of a video. The lower view of the plate is enhanced. MotionDSP

Although that Hollywood hokum is an information-theory impossibility with a single image, some limits are lifted when you have multiple shots of the same scene. And a start-up called MotionDSP is working on commercializing that technology to improve photo and video quality.

The image above demonstrates the technology in action. Clicking the arrow buttons will load different images; my favorite is the mariachi band in the gazebo, in which the process reveals arches and architectural details otherwise lost in noisy murk.

The technology also can get rid of chunky compression artifacts, smooth jagged lines, enrich colors, reveal details, and make text readable. It's an example of computational photography--or videography in this case--in which sophisticated computer processing can improve a photo or video after it was taken.

MotionDSP has been funded by In-Q-Tel, the Central Intelligence Agency's venture investment arm, which naturally is interested in software to extract information from grainy or low-resolution images. But the San Mateo, Calif.-based company is raising a new round of funding to underwrite a more consumer-oriented application of its software, said Chief Executive and founder Sean Varah.

The company showed off its FixMyMovie.com technology for improving lower-grade video at the Demo conference last fall, but the company has other applications of the technology in mind, Varah said.

Most recently, the company added the ability to create a single high-resolution 1280x1024 JPEG image from a 320x240 video. The company also is contemplating use of the technology to stitch together smaller frames into a wide panorama, to improve image tones to retrieve detail in bright highlights and murky shadows. And it's possible, if there's demand, that the company could pursue resolution-enhancing technology to let photography enthusiasts improve their images, Varah said.

Improve your photos?
MotionDSP's technology works by comparing as many as 25 views of the same subject matter. The FixMyMovie site uses the consecutive frames of a video, but the technology also works on a collection of still images.

A burst of five or six images--"it's better if your camera moves a bit"--can be combined into a single still image with four times the resolution, Varah said.

"If you have good 10-megapixel image, do you need to make something bigger? It might make sense if you want to crop or make a billboard," he said.

I suspect there's a significant population that might be interested; some purchase tools like OnOne Software's Genuine Fractals to increase the pixel count of their photos for large-printing purposes. The MotionDSP method might not be a simple process, though, for example in a case with moving subjects.

For videos, FixMyMovie can make several improvements. A video shot with a cell phone at 7.5 frames per second, for example, can be increased to 15 frames per second.

Right now, the Web site is free, but eventually MotionDSP will move it to a "freemium" model in which customers would pay for improvements to longer or higher-resolution videos, Varah said.

Better video from set-top boxes?
MotionDSP also is exploring licensing deals that could enable companies to embed the technology in devices such as set-top boxes. "Everyone wants to take Internet video to the television," but today's low-resolution YouTube videos aren't inspiring on a large screen, he said.

Right now the software takes a little time to improve videos, but with multicore machines growing more common, on-the-fly processing will arrive soon. "I think real-time is less than a year away," Varah said.

The company also is seeking new investors. "We're out raising a round now to take FixMyMovie and really expand on it," Varah said.

One area of interest is building an online service that can be embedded elsewhere--Facebook, for example. Another is improvements to the FixMyMovie site that would let users automatically push videos to one's YouTube account or a blog.

MotionDSP got started about three years ago with technology from the University of California-Santa Cruz. The company now has 18 employees, with much engineering work done in Serbia.