The Pixel phone by Google is one the top smartphones at the market. The camera quality of the Pixel is best among smartphones of its kind. The quality of the camera which Pixel has is possible due to AI. The AI tools used by Google help Pixel to have better shots and shooting modes through a small smartphone camera lens.
As per reports, Google has announced that the AI software which is used by Google Pixel smartphone is going to be open-sourced. The AI code which is open-sourced by Google is named as DeepLab-v3+. This code is used for image segmentation and is built with the help of convolution neural networks (CNN). CNN is a type of machine level language which helps in analyzing the visual data. The main work of the image segmentation is to explain the object present in the picture and split them to foreground elements and background elements.
This is very useful for the cameras, and Google’s Pixel camera portrait mode is based on this process. This mode gives us a bokeh-style image. This style of image is used to blur the background of the image and make the subject pin-point sharp. This effect was bought first by Apple iPhone, and it uses two camera lenses to give portrait effect. The Google pixel uses single camera lens for the same portrait effect.
Google software engineers Liang-Chieh Chen and Yukun Zhu mentioned that the quality of the image segmentation is so high with a deep-learning bloom, that level of accuracy we have now, was hard to think five years ago. The company had said that data is publicly shared so that the researchers can research and produce some better results. Google clarified that the tools which are publicized are not the exact tools that Pixel uses. As a result, the quality of Google Pixel will not get affected.