Here’s a demo of the new program in action. As you can see, the app starts by trying to colorize the image itself, and then it gives you a list of “suggested colors” you can use to help correct mistakes. As you add markers, the software continues to update the image, following your instructions to create something (hopefully) more accurate:
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.
AI-Powered App Helps You Colorize Black & White Photos in Seconds
Color pop desaturates the background while leaving subjects in color. One-tap photo sharing with people identified in photos.
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.
On the left is the original, black and white photo; in the middle is the photo plus some points of color added by Zhang and his team, telling the computer what shade that area should be; and on the right we have the final colorized photograph:
Colorize Photos Use Deep Learning to Automatically Colorize Black and White Photos
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.
The fact of the matter is, the neural network-powered algorithm is really good at applying color to black and white photos, but it’s often bad at guessing what color any particular item of clothing, inanimate object, or even person should be. Letting you play “middleman” in this scenario is a simple solution to this problem.
This is amazing. The researchers at UC Berkeley who came up with the automatic colorizer algorithm we first shared back in March, 2016 have released a major update. The software now lets you team up with the algorithm to colorize complex black and white photos accurately in seconds.
Tags: ai, automatic, awesome, blackandwhite, color, colorize, convolutedneuralnetwork, cool, impressive, machinelearning, neuralnetwork, powerful
Image credits: All photographs via Richard Zhang/UC Berkeley.
Here are a few examples from the UC Berkeley website, showing how Zhang’s team colorized some iconic black and white photos from history.
Black and white photo + a few colored dos = fully colorized image. That would be a game changer.
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.
We hope Adobe is listening, and we hope they’re working on this right now. But even if they’re not, you can download Zhang’s creation from Github and give it a shot for yourself.
You can start using some of these powerful new features today by downloading the latest version of Google Photos for iOS and Android.
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).
Both the original app and this update were created by Richard Zhang and his team at UC Berkeley. But while the original often got many of the colors wrong, the update lets you give the algorithm “hints” so that it knows what color goes where.
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):
Tags: ai, artificialintelligence, autocolorization, colorization, colorize, google, googlei/o, googlephotos
The before-and-after colorization example shown at Google I/O 2018.
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
Fully automatic colorization feels like science fiction—something we will probably see SOME day in Photoshop, but not someday soon. This update application, on the other hand, feels like it could be included in the next version of the software.
Of course, you can also mess with the algorithm, giving it “bad hints” as it were and watching the computer colorize a pink beard onto Earnest Hemingway… for example: