homehome Home chatchat Notifications


New algorithm turns low-resolution photos into detailed images -- CSI style

Zoom in on that license plate. Yes, I see it clearly now...

Mihai Andrei
November 6, 2017 @ 6:17 pm

share Share

You know that stereotypic scene from the CSI movies when they zoom in on a car they can barely see and then read the license plate clearly? Well, that bit of fiction might turn into reality, as computer scientists from the Max Planck Institute for Intelligent Systems in Tübingen have used artificial intelligence to create high-definition images from low-resolution photos.

EnhanceNet-PAT is capable of upsampling a low-resolution image (left) to a high definition version (middle). The result is indistinguishable from the original image (right). Credit: Max Planck Institute for Intelligent Systems.

It’s not the first time researchers have looked at something like this. The technology is called single-image super-resolution (SISR). SISR has been researched for decades, but without much success. No matter how you look at it, the problem was that they just didn’t have enough pixels to generate a sharp image.

Now, researchers developed a tool called EnhanceNet-PAT, which uses AI to generate new pixels and “fill” the image up.

“The task of super-resolution has been studied for decades,” Mehdi M.S. Sajjadi, one of the researchers on the project, told Digital Trends. “Before this work, even the state of the art has been producing very blurry images, especially at textured regions. The reason for this is that they asked their neural networks the impossible — to reconstruct the original image with pixel-perfect accuracy. Since this is impossible, the neural networks produce blurry results. We take a different approach [by instead asking] the neural network to produce realistic textures. To do this, the neural network takes a look at the whole image, detects regions, and uses this semantic information to produce realistic textures and sharper images.”

First, the neural network was fed a large data set of different images. It learned different textures and colors. Then, it was given downscaled images which it had to improve. The upscaled results were then compared to the initial photo, with the algorithm analyzing and learning from these differences. After a while, it did a good enough job without any human input.

Of course, this isn’t a magic fix and not all photos can be fixed (at least not yet), but results are exciting. As for the applications, there’s no shortage of those, Sajjadi says. The algorithm could be used to restore old family photos or give them a good enough resolution for larger prints; on a more pragmatic level, the technology could greatly help in object recognition, which has potential in detecting pedestrians and other objects in self-driving cars.

Journal Reference: Mehdi S. M. Sajjadi, Bernhard Schölkopf, Michael Hirsch. EnhanceNet: Single Image Super-Resolution Through Automated Texture Synthesis.

share Share

Tennis May Add Nearly 10 Years to Your Life and Most People Are Ignoring It

Could a weekly match on the court be the secret to a longer, healthier life?

Humans Have Been Reshaping Earth with Fire for at Least 50,000 Years

Fossil charcoal reveals early humans’ growing impact on the carbon cycle before the Ice Age.

The Strangest Microbe Ever Found Straddles The Line Between Life and Non-Life

A newly discovered archaeon blurs the boundary between cells and viruses.

This $8750 Watch Was Designed for Space and Could Finally Replace Apollo-era Omega Watches

An audacious new timepiece dares to outshine Omega’s legacy in space

The Brain May Make New Neurons in Adulthood and Even Old Age

Researchers identify the birthplace of new brain cells well into late adulthood.

Your gut has a secret weapon against 'forever chemicals': microbes

Our bodies have some surprising allies sometimes.

High IQ People Are Strikingly Better at Forecasting the Future

New study shows intelligence shapes our ability to forecast life events accurately.

Cheese Before Bed Might Actually Be Giving You Nightmares

Eating dairy or sweets late at night may fuel disturbing dreams, new study finds.

Scientists Ranked the Most Hydrating Drinks and Water Didn't Win

Milk is more hydrating than water. Here's why.

Methane Leaks from Fossil Fuels Hit Record Highs. And We're Still Looking the Other Way

Powerful leaks, patchy action, and untapped fixes keep methane near record highs in 2024.