The AI behind Pixel's super-high portrait mode is launched by Google into open source
Camera on Google's Pixel phone is one of the best cameras available today, and one of the main reasons is the AI system behind it. Google uses machine learning technology to select the best pictures. And now, they are planning to turn one of these AI tools into open source tools.
Posted on the blog earlier this week, Google launched the open source version of DeepLab-v3 +. This is an image partitioning tool using Convolutional Neural Network (CNN). A machine learning method is very good at analyzing image data. Partition the image to analyze the object in the image, divided into regions, split the image in the foreground and background in the image.
How the image partition works
While it may sound normal, this method is very useful for cameras and Google uses it for its Pixel portrait mode. The result was bokeh-style images, blurring the background but the subject was still clear.
The iPhone itself made the technology popular, but it should be noted that Apple uses two lenses to create a portrait effect, while Google uses only one. (And the portrait mode of Apple or Google is better, readers should judge for themselves).
According to the explanation of software engineer Google Liang-Chieh CHen and Yukun Zhu, image partitioning has improved rapidly thanks to the flourishing of deep learning, reaching 'unimaginable accuracy in the past 5 years'. . Google hopes to share widely with 'other groups in the industry to continue to improve' the work they have done.
Bringing such software to the community will help application developers when they need image partitioning technology, and catch up with Google.
https://github.com/tensorflow/models/tree/master/research/deeplab
See more:
- This is a portrait shot that removes fonts (Portrait Mode) on Pixel 2 without Pixel 2
- This is why you should buy Pixel 2 instead of iPhone X
- Compare the best photography smartphones in 2017
You should read it
- How to take a photo in Portrait and Portrait Lighting mode on iPhone 7 Plus and 8 Plus
- How to take a Portrait mode on Android
- Google researchers for gaming AI to improve enhanced learning ability
- Top smartphones take pictures 'best fonts'
- How to take Portrait Mode selfie photos on iPhone X
- Take professional portraits with your iPhone with Portrait Mode
- What is machine learning? What is deep learning? Difference between AI, machine learning and deep learning
- How to switch focal length in Portrait Mode on iPhone 11 Pro
May be interested
- The 34 best and worst phones in Nokia's calendar, which one is your spring?looking back at the memorable and impressive phone models of the phone company that has been known throughout the world for 30 years.
- Microsoft rewards $ 250,000 for any talent that discovers the new Meltdown and Specter vulnerabilitiesin the effort to protect users from meltdown and specter vulnerabilities, microsoft has decided to launch a 'bounty hunt' program with extremely lucrative expenses for anyone who finds new security flaws. and reveal them to microsoft.
- Pokémon play screen with interface coming from the future fever in Japanrecently, game developers in japan introduced a real pokédex play screen, identical to the hologram design, allowing gamers to access pokémon data in a way that is not more modern.
- Samsung's QLED 2018 4K TV hides into the wall and controls smart homeof course they are also integrated with bixby.
- Facebook adds video calling for Messenger Litewith the addition of this new video call feature, the collapsed messenger lite has almost all the features of the full version while ensuring that it does not increase the capacity or consume too much resources.
- The scary ghost in The Ring comes out of the TV screen thanks to ARKit technologythanks to arkit technology, programmer abhishek singh helped the terrifying samara ghost in the ring get out of the screen, even chasing you around the house.