Hey Mi Fans,
Welcome to yet another Tech Wednesday !
Today we'd be talking about AI photography and how does it revolutionize smartphone photography experience.
Smartphone manufacturers use machine learning to develop image recognition engines which make use of a neural network trained on millions of images.
From this machine learning, an AI camera develops the knack for automatically identifying scenes, available light and even the angle the of the scene. As such, your camera knows that it’s looking at a person, food, nature, animals, e.t.c. Subsequently, the AI camera chooses the most applicable exposure and colour adjustments for that perfect shot.
AI Photography helps to save time by smartly performing the requiredimage processing in real time, that required hours of working with the image on Photoshop or Lighthouse or any of the commercial grade image editing software.
Google set up a deep neural network trained on data that had been labeled by humans. This is called supervised learning.
The process involves training the network on millions of images so that it can look for visual clues at the pixel level to help identify the category. Over time, the algorithm gets better and better at recognizing. Other companies like Apple too developed a similar algorithm to search photos, auto modify shots etc.
With AI photography, megapixel count doesn't matter anymore, Google has proved it ! What matters the most is the computational skills or the NPU's (some phones have dedicated chips to do the photography advancements).
The "computational skills" cover everything from the fake depth-of-field effects in phones’ portrait modes to the algorithms that help drive the Pixel’s incredible image quality, making its 12MP photos beat even 40 MP photos by other OEMs.
What Are Your Thoughts On AI Photography ?
In order to fulfill the basic functions of our service, the user hereby agrees to allow Xiaomi to collect, process and use personal information which shall include but not be limited to written threads, pictures, comments, replies in the Mi Community, and relevant data types listed in Xiaomi's Private Policy. By selecting "Agree", you agree to Xiaomi's Private Policy and Content Policy .