Experts Successfully Trained An AI To Fix Distorted Underwater Pictures

Aadhya Khatri - Jan 02, 2020


Experts Successfully Trained An AI To Fix Distorted Underwater Pictures

The AI has the ability to de-haze images with green tones without ruining the original structure of the pictures

As a result of back-scattering and light attenuation, pictures taken underwater tend to be distorted and blurry. To save photos affected by these phenomena, experts from the Harbin Engineering University proposed a solution, which comes in the form of two AI systems, one can produce realistic underwater pictures, the other learns from what the first one makes and then fix the distorted images.

The team pointed out that the majority of other picture-enhancing systems work without taking the physical imaging models into consideration, so they do not exactly do the task well.

AI-de-haze-underwater-pictures
The last benefit is that the system is able to maintain the color contrast and brightness over the process

The first AI is called GAN and it is trained with a corpus of 3,733 scenes with labels and their depth maps, mostly consist of sea cucumbers, scallops, sea urchins, and other underwater organisms living in marine farms. They also used some other open datasets, like NY Depth, a library of thousands of photos taken underwater.

After some tests, the researchers said that their approach has the following advantages over others. The first one is the uniform in color restoration; the second is the ability to de-haze images with green tones without ruining the structure of the pictures. The last benefit is that the system is able to maintain the color contrast and brightness over the process.

Experts from Harbin Engineering University were not the first ones to try restoring distorted pictures. We have seen DeepRay, Cambridge Consultants' Digital Greenhouse internal incubator. It was trained with 100,000 still pictures distorted by an opaque pane of glass. Another effort results in DeOldify, a system that can restore and colorize old footage and images.

Microsoft also has its fair share of the work in the form of automatic video colorization. Google has its own algorithm for grayscale colorization without the supervision of humans.

Comments

Sort by Newest | Popular

Next Story

Read more

These Living Bricks Can Self-Heal, Absorb CO2, And Multiply

Features- Jan 16, 2020

These Living Bricks Can Self-Heal, Absorb CO2, And Multiply

The resulting bricks are as durable as any other ones on the market, as shared by Wil Srubar, assistant professor of the University of Colorado Boulder

All You Can Do With The Long-Press On Safari

How To- Jan 16, 2020

All You Can Do With The Long-Press On Safari

Here we will provide you 10 tips to take full advantage of the long-press on iPads and iPhones running iOS 13

How To Enable Two-Factor Authentication On Facebook

How To- Jan 16, 2020

How To Enable Two-Factor Authentication On Facebook

You should enable two-factor authentication on Facebook as soon as possible.

Black Shark 3 Tipped To Carry 120Hz Quad-HD+ Display & Whopping 16GB RAM

Mobile- Jan 16, 2020

Black Shark 3 Tipped To Carry 120Hz Quad-HD+ Display & Whopping 16GB RAM

The upcoming Xiaomi Black Shark 3 could be a beast when it launches with the 120Hz Quad-HD+ display and a whopping 16GB of RAM.

Instagram Is Testing Direct Messages On The Web

ICT News- Jan 16, 2020

Instagram Is Testing Direct Messages On The Web

Instagram is reportedly testing the messaging function on the web, which is currently only available on its mobile app

First Mission OF 2020: ISRO To Launch GSAT-3 To Improve Internet And TV Signals

Features- Jan 16, 2020

First Mission OF 2020: ISRO To Launch GSAT-3 To Improve Internet And TV Signals

The satellite has a huge weight of 3,357 kilograms and will replace the INSAT-4A, providing better coverage, expected to operate for the next 15 years.