We are reader supported. External links may earn us a commission.

Android

Google open sources Pixel 2 Portrait Mode segmentation software

By Jules Wang March 14, 2018, 7:13 pm

The code that Google used on its Pixel 2 smartphones to determine what to blur and what to focus on in Portrait Mode pictures is now free for developers to use in their own apps.

Google Research has detailed what it calls its machine-learning semantic image segmentation model, DeepLab-v3+. The composite model, which implements Google’s TensorFlow neural network processing as well as models such as Pascal and Cityscapes, essentially determines what items in the image are classified as human, animal, food or some other genre as well as define specific ranges for these items. From there, the model can determine what the background is and what key subjects are.

POCKETNOW VIDEO OF THE DAY

On the Pixel 2 and Pixel 2 XL, this data is used for Portrait Mode where the background is blurred and the subjects are kept in focus, but it is hoped that “other groups in academia and industry” will reproduce results for their own purposes and even expand upon DeepLab’s model for further refinement.

Search

Latest Articles

Phones

These are the best Moto G Power 2022 Cases

This article will show you some of the best rugged, slim and lightweight, transparent, and colorful cases that we could find on Amazon for the Motorola Moto G Power 2022.

By Roland Udvarlaki May 26, 2022, 1:20 pm