Breaking News

Samsung Display to Introduce First 90Hz OLED Laptop Display addlink launch P20 Portable SSD speed of up to 1050MB/s aKASA announces RGB controllers the new SOHO and VEGAS XL A Brief History of the Galaxy S Series’ Camera Technologies Samsung Introduces the 870 EVO SATA SSD Series

logo

  • Share Us
    • Facebook
    • Twitter
  • Home
  • Home
  • News
  • Reviews
  • Forum
  • Legacy
  • About
    • Submit News

    • Contact Us
    • Privacy

    • Promotion
    • Advertise

    • RSS Feed
    • Site Map

Search form

Researchers Recover Blurred Images and Videos

Researchers Recover Blurred Images and Videos

Enterprise & IT Oct 17,2019 0

MIT researchers have developed a model that recovers data lost from images and video.

The model could be used to recreate video from motion-blurred images, or from new types of cameras that capture a person’s movement around corners but only as vague one-dimensional lines. While more testing is needed, the researchers think this approach could someday could be used to convert 2D medical images into more informative — but more expensive — 3D body scans, which could benefit medical imaging in poorer nations.

The model is described in a paper that will be being presented at next week’s International Conference on Computer Vision, authored by Guha Balakrishnan, a postdoc in Computer Science and Artificial Intelligence Laboratory (CSAIL).

Captured visual data often collapses data of multiple dimensions of time and space into one or two dimensions, called “projections.” X-rays, for example, collapse three-dimensional data about anatomical structures into a flat image.

Likewise, “corner cameras,” recently invented at MIT, detect moving people around corners. These could be useful for, say, firefighters finding people in burning buildings. But the cameras aren’t exactly user-friendly. Currently they only produce projections that resemble blurry, squiggly lines, corresponding to a person’s trajectory and speed.

The researchers invented a “visual deprojection” model that uses a neural network to “learn” patterns that match low-dimensional projections to their original high-dimensional images and videos. Given new projections, the model uses what it’s learned to recreate all the original data from a projection.

In experiments, the model synthesized accurate video frames showing people walking, by extracting information from single, one-dimensional lines similar to those produced by corner cameras. The model also recovered video frames from single, motion-blurred projections of digits moving around a screen, from the popular Moving MNIST dataset.

The researchers built a general model, based on a convolutional neural network (CNN) — a machine-learning model that’s become a powerhouse for image-processing tasks — that captures clues about any lost dimension in averaged pixels.

In training, the researchers fed the CNN thousands of pairs of projections and their high-dimensional sources, called “signals.” The CNN learns pixel patterns in the projections that match those in the signals. Powering the CNN is a framework called a “variational autoencoder,” which evaluates how well the CNN outputs match its inputs across some statistical probability. From that, the model learns a “space” of all possible signals that could have produced a given projection. This creates, in essence, a type of blueprint for how to go from a projection to all possible matching signals.

When shown previously unseen projections, the model notes the pixel patterns and follows the blueprints to all possible signals that could have produced that projection. Then, it synthesizes new images that combine all data from the projection and all data from the signal. This recreates the high-dimensional signal.

For one experiment, the researchers collected a dataset of 35 videos of 30 people walking in a specified area. They collapsed all frames into projections that they used to train and test the model. From a hold-out set of six unseen projections, the model accurately recreated 24 frames of the person’s gait, down to the position of their legs and the person’s size as they walked toward or away from the camera. The model seems to learn, for instance, that pixels that get darker and wider with time likely correspond to a person walking closer to the camera.

“It’s almost like magic that we’re able to recover this detail,” Balakrishnan says.

The researchers are now collaborating with Cornell University colleagues to recover 3D anatomical information from 2D medical images, such as X-rays, with no added costs — which can enable more detailed medical imaging in poorer nations. Doctors mostly prefer 3D scans, such as those captured with CT scans, because they contain far more useful medical information. But CT scans are generally difficult and expensive to acquire.

“If we can convert X-rays to CT scans, that would be somewhat game-changing,” Balakrishnan says. “You could just take an X-ray and push it through our algorithm and see all the lost information.”

Tags: MIT
Previous Post
Panasonic to Launch Ride-sharing Service With Autonomous Vehicles
Next Post
MSI Offers up to €70 Cashback for Selected Combo Deals of MSI Z390 Motherboard and Intel CPU

Related Posts

  • MIT Researchers Says New Coronavirus Contact Tracing App Preserves Privacy

  • MIT's Cheetah Robot Can Do a Backflip

  • Researchers Use Lasers to Send a Whispered Audio Message to You Only

  • Researchers Convert Wi-Fi signals to Electricity

  • MIT Researhers Create a Faster and More Efficient Cryptocurrency

  • Researchers Accelerate 3-D Printing

  • Engineers Fly First-ever Plane Powered by Flow of Ions

  • MIT Launches Online Learning Initiative

Latest News

Samsung Display to Introduce First 90Hz OLED Laptop Display
Enterprise & IT

Samsung Display to Introduce First 90Hz OLED Laptop Display

addlink launch P20 Portable SSD speed of up to 1050MB/s
PC components

addlink launch P20 Portable SSD speed of up to 1050MB/s

aKASA announces RGB controllers the new SOHO and VEGAS XL
PC components

aKASA announces RGB controllers the new SOHO and VEGAS XL

A Brief History of the Galaxy S Series’ Camera Technologies
Smartphones

A Brief History of the Galaxy S Series’ Camera Technologies

Samsung Introduces the 870 EVO SATA SSD Series
PC components

Samsung Introduces the 870 EVO SATA SSD Series

Popular Reviews

CeBIT 2005

CeBIT 2005

Zidoo Z9S 4K Media Player review

Zidoo Z9S 4K Media Player review

CeBIT 2006

CeBIT 2006

LiteOn iHBS112 review

LiteOn iHBS112 review

Club3D HD3850

Club3D HD3850

Crucial P1 NVMe 1TB SSD review

Crucial P1 NVMe 1TB SSD review

Hitachi DZ-MV100A DVD Camcorder

Hitachi DZ-MV100A DVD Camcorder

Toshiba Exceria M303 64GB and M501 Exceria Pro 64GB MicroSDXC review

Toshiba Exceria M303 64GB and M501 Exceria Pro 64GB MicroSDXC review

  • Home
  • News
  • Reviews
  • Forum
  • Legacy
  • About
    • Submit News

    • Contact Us
    • Privacy

    • Promotion
    • Advertise

    • RSS Feed
    • Site Map
  • About
  • Privacy
  • Contact Us
  • Promotional Opportunities @ CdrInfo.com
  • Advertise on out site
  • Submit your News to our site
  • RSS Feed