Google used 64 cameras for Portrait Light

Google has published a blog explaining the technology behind the Portrait Light feature, including how to train its models for machine learning.

And Google’s Portrait Light feature can make some of your modest photos look a whole lot better by giving you a way to change the direction and intensity of lighting.

Google launched its AI-based lighting feature in September for Pixel 4a 5G and Pixel 5 phones, before giving older Pixel phones access.

The company needed millions of images with additional lighting from different directions and without additional lighting from different directions, in order to be able to train one of these models to add lighting to an image from a specific direction.

The company used a spherical illumination device with 64 cameras and 331 individually programmable LED light sources to capture the images you need.

It photographed 70 people with different face colors, face shapes, genders, hairstyles, and even clothes and accessories, highlighting them inside the device through one light at a time.

The company has also trained a template to select the best lit selfie for automatic lighting mode, and the post includes all the technical details.

The Pixel Camera on Pixel 4, Pixel 4a, Pixel 4a 5G and Pixel 5 devices automatically applies the Portrait Light feature by default and through Night Sight photos that people have.

You can find the option to turn the feature on under the settings section when editing a photo of a person on older Pixel phones.

You have to take the photo in Portrait Mode and edit the photo through Google Photos if you want to be able to manually reposition the lighting and adjust its brightness.

Google produces some of the best still images with Pixel phones, and they are the result of hard artwork and lots of machine learning models.

It is reported that Google is not the first smartphone manufacturer to introduce Portrait lighting effects to its customers, but it may have done so using a large number of advanced algorithms and machine learning models.

Related Stories

Stay on op - Ge the daily news in your inbox

Recent Articles