I guess, mostly everyone agrees with the fact that the Pixel cameras are the best camera on a smartphone chassy till date.
Now Google has open Sourced a part of software magic that the Pixel cameras would do to gets the awesome portrait mode bokeh effect photos As announced in a blog post earlier this week. Just to be clear Google has not the technology behind their camera or the portrait effect.
The open Sourced just a part of the whole technology. Google has open-sourced an of code name DeepLab-v3+. This is an image segmentation tool built using convolutional neural networks, or CNN’s (a machine learning method that’s particularly good at analyzing visual data).
Image segmentation analyzes objects within a picture, and splits them apart, dividing foreground elements from background elements.
Basically, it categorizes every pixel with a label such as “person” or “sky.” This helps the camera to differentiate between a person in the foreground and the sky in the background. And which in turn contributes to the bokeh effect. Google has released this technology as open source, which means developers can use the same technology in their own apps. Portrait Mode is just one example of how this technology can be used. Developers can do even more cool stuff.
For more information on the article click here.
(*Note: This not the technology that is behind the Google Pixel 2 and Google Pixel 2 XL camera it’s just a small part of the technology behind it.)