Knowing that, this is an impressive demo indeed, and a small taste of what could be in store for photographers and retouchers with everyday photo-editing software in the future.
Want a taste of the future? There’s a new web app that uses advanced “deep learning” research to magically auto-colorize black-and-white photos.The app uses the Colorful Image Colorization algorithm that’s being developed by a team at UC Berkeley led by PhD student Richard Zhang. We first reported on the technology back in March 2016, and now there’s an online demo that anyone can try on any photograph.
While the neural network is good at certain subjects such as turning grass green, others, like nailing the skin tones on people, are a lot more challenging. So, Google is working to improve the feature and won’t be launching it until it’s “really right,” the company tells TechCrunch.
Google is taking to the stage at the Google I/O developer conference this week to show off its new products and technologies, one of which is a new AI-powered version of Google Photos. The new app will feature a host of new intelligent features, including the ability to colorize black-and-white photos with one tap.The “Colorize” tool uses artificial intelligence to make a “best guess” of what a color version of an old monochrome photo would have looked like.
Google is also baking a host of other AI-powered features into Google Photos, including automatic content creation (collages, animations, movies), automatic photo enhancements (e.g. brightening dark photos, rotating, and desaturating the background of portraits), and facial recognition (e.g. recognizing people in photos and asking if you’d like to share with them).
Here are a couple of example colorizations provided by the app’s creators:
Colorization has traditionally been done by Photoshop experts who spend hours upon hours researching colors and meticulously converting small portions of photos at a time. But researchers have been making huge strides in teaching AI how to colorize images through learning from examples. Simple apps and websites have also emerged to provide auto-colorization.
Colorize Photos Use Deep Learning to Automatically Colorize Black and White Photos
Tags: ai, algorithmia, artificialintelligence, autocolor, autocolorization, autocolorize, b&w, blackandwhite, color, colorize, deeplearning, demo, future, machinelearning, technology, test
It’s easier than ever to take action on your pictures in @googlephotos. Rolling out today, you may start to see suggestions to brighten, archive, share, or rotate your photos, right on the image. #io18 pic.twitter.com/NPT0l0GuBy
Tags: ai, artificialintelligence, autocolorization, colorization, colorize, google, googlei/o, googlephotos
The before-and-after colorization example shown at Google I/O 2018.
Simply paste a URL to a photo into the website and press the purple “Colorize It” button. After some processing and a short wait, the page displays a side-by-side comparison of the B&W and colorized photos that you can switch between.
With Google’s vast image libraries, world-class researchers and developers, and AI prowess, though, we may soon see some colorization results that push the envelope in terms of what’s possible.
And here are some of the results we got from testing the app ourselves:
If these colorizations were created by a human retoucher, you’d probably think they were horribly done by someone lacking in talent. But what’s impressive is that the color was completely added by artificial intelligence without any human intervention — the computer simply “learned” what colors to use by learning from over 1 million other photos.
Head on over to the web app if you’d like to try it out on your own B&W photo.
You can start using some of these powerful new features today by downloading the latest version of Google Photos for iOS and Android.
Color pop desaturates the background while leaving subjects in color. One-tap photo sharing with people identified in photos.
You can watch Google CEO Sundar Pichai introduce these new Google Photos features during the Google I/O keynote yesterday in this video (it starts at 1:33:15):