Skip to main content

How does Google's Real Tone camera feature work?

Best answer: The same machine learning that helps improve portrait photos and power Magic Eraser also makes the Pixel 6 camera more inclusive for all skin tones through its Real Tone feature.

What is Real Tone?

Google developed its Real Tone camera tech with a mission to make its camera and image products more equitable when photographing people of color, especially for those with darker skin tones. Historically, a lack of diverse testing meant that today's cameras weren't built to accurately portray all skin tones in their natural beauty. Unfortunately, this also means that smartphones continue to carry that bias, ultimately delivering unflattering photos for people of color. But it's not just smartphone cameras that struggle here. We've seen all sorts of camera-enabled tech issues when it comes to people who aren't light-skinned.

So with the launch of its Pixel 6, Google is trying to tackle this issue using Real Tone. With this feature, the camera hardware and software work in tandem to match the actual tone of the people in frame. And it works surprisingly well, especially for a first-generation product.

How it works isn't that simple to explain without sounding like there's a good bit of magic at play. But really, it's no different than any other aspect of computational photography that powers the best Android camera phones. It just needed a company to spend the time and money to work on it.

When you tap the shutter button in the camera app on your phone, the work of building a great photograph has already started. Camera lenses and sensors aren't particularly smart, but they're very good at their intended purposes: collecting and focusing light. Using multiple captures and electronic filters, sensor data is collected at very specific points of light in colors red, blue, and green.

That data isn't a photo, though. It's just data. It takes some processing to turn millions of individual points of light into an image, and that's where Google has always been really good at the game. Using machine learning and AI, the camera stream can look for shapes and contrasts to build a face, differentiate between the subject and the background, and more. One of the very important things that need to happen to camera sensor data is to make the colors in the finished photograph look the same as what a human eye can see.

That's where Real Tone shines. The camera software was refined to evaluate the skin tones it sees and expands on the number of different shades it thinks a person can be. Think about the people you know and how different the color of their skin can be from each other or from yours. Humans aren't just beige or brown, and camera software shouldn't act like they are. If you're a white person like I am, you probably haven't ever had an issue with your skin color in photos. But a lot of people always have.

This wasn't an easy undertaking — but it was a necessary one. Over-brightening darker skin or applying less contrast just doesn't work, and we have billions of photos that prove it. Something like Google's Real Tone project is long overdue.

Our Pick

Google Pixel 6 - 5G

From $599 at Amazon From $599 at Best Buy From $599 at B&H

Finally, a proper Pixel flagship has arrived.

After years of fatal flaws and stagnant design, Google has finally given us the shock-and-awe upgrade we've been waiting for. Tensor's AI prowess makes most Assistant features feel magically fast. Major camera updates for hardware and processing give us significantly better photos, especially when photographing people of color and moments of action.



Source: androidcentral

Popular posts from this blog

FCC approves broadband 'nutrition labels' to help you shop for internet

The FCC is pushing nutrition labels for internet providers. What you need to know The FCC has voted to move forward with new rules for ISPs to display nutrition labels. The proposed rulemaking would mandate ISPs to display relevant speed and pricing information to consumers. This should make it easier for consumers to make an informed decision on their broadband. The FCC voted unanimously on a plan that would allow consumers to make better decisions about their broadband internet. The proposal will require internet service providers (ISPs) - including many of the best wireless carriers in the U.S. — to display "nutrition labels" that display relevant service information for consumers at point-of-sale. This includes internet speeds, allowances, and clear information on rates. "If you walk into any grocery store and pull boxes of cereal from the shelves, you can easily compare calories and carbohydrates," FCC Chair Jessica Rosenworcel said in a statemen

Slack’s new integration deal with AWS could also be about tweaking Microsoft

Slack and Amazon announced a big integration late yesterday afternoon. As part of the deal, Slack will use Amazon Chime for its call feature, while reiterating its commitment to use AWS as its preferred cloud provider to run its infrastructure. At the same time, AWS has agreed to use Slack for internal communications. Make no mistake, this is a big deal as the SaaS communications tool increases its ties with AWS, but this agreement could also be about slighting Microsoft and its rival Teams product by making a deal with a cloud rival. In the past Slack CEO Stewart Butterfield has had choice words for Microsoft saying the Redmond technology giant sees his company as an “existential threat.” Whether that’s true or not — Teams is but one piece of a huge technology company — it’s impossible not to look at the deal in this context. Aligning more deeply with AWS sends a message to Microsoft, whose Azure infrastructure services compete with AWS. Butterfield didn’t say that of course

Yandex spins out self-driving car unit from its Uber JV, invests $150M into newco

Self-driving cars are still many years away from becoming a ubiquitous reality, but today one of the bigger efforts to build and develop them is taking a significant step out as part of its strategy to be at the forefront for when they do. Yandex — the publicly-traded Russian tech giant that started as a search engine but has expanded into a number of other, related areas (similar to US counterpart Google) — today announced that it is spinning out its self-driving car unit from MLU BV — a ride-hailing and food delivery joint venture it operates in partnership with Uber. The move comes amid reports that Yandex and Uber were eyeing up an IPO for MLU  last year. At the time, the JV was estimated to be valued at around $7.7 billion. It’s not clear how those plans will have been impacted in recent months, with COVID-19 putting huge pressure on ride-hailing and food-delivery businesses globally, and IPOs generally down compared to a year ago. In that context, spinning out the unit could

Elon Musk sends yet another notice trying to terminate the Twitter deal

Kristen Radtke / The Verge; Getty Images Elon Musk has sent a third letter to Twitter attempting to terminate his $44 billion acquisition of the company . Musk’s legal team cited Twitter’s multimillion dollar severance payment to former security chief and whistleblower Peiter Zatko as a violation of the merger agreement and a reason to end the deal. The letter, dated September 9th, was sent to Twitter’s chief legal officer Vijaya Gadde, and was included in a filing Twitter made with the SEC on Friday (which you can read at the bottom of this article). Last month, Zatko made headlines by accusing Twitter of misleading investors about the number of bots on the service, failing to delete users’ data, and having poor security practices, among other things. Musk jumped on the accusations, citing them in his second termination letter and subpoenaing Zatko to testify in the lawsuit. Zatko was set to be deposed on Friday. Elon Musk sent his first letter of termination in July , say