With Real Tone, Pixel 6 aims to enhance your portraits, whatever your skin tone – TechCrunch


It makes sense for phone makers to pay close attention to how faces appear in photos, and the new Pixel 6, announced by Google today, introduces a suite of new AI-powered tools for people to use. humans look better than ever. The two highlights are Face Unblur – which helps reduce blur on moving faces – and Real Tone. The latter is AI-powered post-processing magic – powered by Google’s all-new Tensor chip – aimed at making faces appear as good as possible with all skin tones.

Whether you take selfies or selfies, the vast majority of photos taken with a smartphone are of human beings. Traditionally, it has been extremely difficult to get good exposure for photos where multiple faces appear in the photo, especially if the faces all have different skin tones. The new Pixel 6 brings a layer of computer photography to the mix to make sure everyone in the photo looks as good as it gets. The Pixel team worked with a diverse set of expert image makers and photographers to adjust white balance, exposure, and algorithms. They claim this ensures that the photos work for everyone, of all skin tones.

Google stresses that it sees Real Tone as a mission and an improvement on its camera systems, rather than a conclusive solution to the challenges photographers face. The company has invested substantial resources to ensure that all people – and especially people of color – are better represented in the way cameras capture their faces.

“My mother is a dark-skinned black woman, my father is a white German. All my life, a question has been asked: how do we get an image where everyone looks good, ”said Florian Koenigsberger, Advanced Photography product marketing manager for the Android team, in an interview information ahead of the release of the new phones. “The new camera is a step on the way. Google’s diversity numbers are no mystery to the world, and we knew we certainly had some shortcomings in terms of lived experience and who could speak about it in an authentic way.

The camera team worked with photographers, colorists, cinematographers, cinematographers and directors to better understand the challenges of lighting and capture a diverse set of skin tones – and in particular people with darker skin tones. Among others, the team drew on the experience of a wide range of professionals, including Ava Berkofsky, director of photography at Insecure, photographer Joshua Kissi and director of photography Kira Kelly.

“We focused on bringing this set of very diverse perspectives, not only in terms of ethnicity and skin tones, but also a variety of practices,” Koenigsberger said. “Colorists were actually some of the most interesting people to talk to because they see this as a science that happens in the process of creating images. “

The Google product team worked with these imaging experts to provide them with cameras and challenged them to shoot extremely difficult imaging situations, including mixed light sources, backlighting, interiors, multiple skin tones in a single image, etc.

“We had to learn where things are falling apart, especially for these communities, and from there we can determine which direction we can take from there,” says Koenigsberger. “The imaging professionals were very outspoken, and they were right in the room with our engineers. I helped facilitate these conversations, and it was fascinating to see not only the technical learnings but also the cultural learning that took place in this space. I’m talking ash, darker skin tones, textures. Shades of midtones may vary.

The process begins with the face detection algorithms of the camera. Once the camera knows it’s looking at a face, it can begin to figure out how to render the image in a way that works well. When testing on multiple devices, the Google team found that the Pixel 6 still performed better than those from competing manufacturers, and even older generation Pixel phones.

It’s not immediately clear how the feature works in practice, and whether it does global edits (i.e. applies the same filter to the entire image) or if the AI ​​edits individual faces in the image. as part of his editing pass. We hope to take a closer look at this specific aspect of camera functionality to see how it works in practice very soon.

The camera team points out that the work being done in this space means that the training sets for creating the camera algorithms are more diverse by a factor of 25. The Real Tone function is an essential part of the algorithms of the camera. camera, and it cannot be turned off or off.

Source link


Leave A Reply