>
Google has been a pioneer of computational photography in recent years and its latest trick, called ‘Photo Unblur’, could be one of the most impressive tricks yet. A Google Photos feature that will be exclusive to the Pixel 7 and Pixel 7 Pro initially, it promises to save your new and old photos from blurry oblivion.
Photo Unblur is an extension of ‘Face Unblur’, which appeared on the Pixel 6 and Pixel 6 Pro last year. The latter has quickly become one of the most popular computational photography features since Google unveiled “Night Sight” on the Pixel 4 in 2019. But it’s also very different from Photo Unblur, meaning the two will act as complementary modes for different situations.
Both features use machine learning to enhance your photos, but Photo Unblur is designed to enhance the photos you’ve already taken with a camera. Face Unblur, meanwhile, is a preventative mode that uses the power of Google’s Tensor chip to detect when someone is moving too fast in your scene. Two photos are then automatically taken, which are combined and you get a well-exposed, sharp photo.
So how exactly does Google’s new Photo Unblur mode work without getting multiple snaps of the same scene? Google hasn’t fully expanded its inner workings yet, but we can get a good idea by looking at where it comes from.
How does Photo Unblur work?
Photo Unblur didn’t come completely out of the blue – while Google hasn’t expanded its inner workings yet, it’s likely built on some of the existing features we’ve seen in the Google Photos app. And that means it could eventually be available on devices outside of the Pixel 7 and Pixel 7 Pro.
In 2021 the Google AI blog (opens in new tab) described the technology behind two new Google Photos features called “Denoise” and “Sharpen.” These came to help you improve photos taken in tricky conditions, or with older phones with noisy sensors or old optics. And these are probably the foundation of Photo Unblur.
Photo editors have long had sliders to help you adjust noise and sharpening, but Google’s new technology is much smarter than that. For starters, it analyzes your entire image to determine the levels of noise and blur down to the pixel level, regardless of what camera the photos were taken with.
This crucial step ensures that noise reduction and blurring take place at a more detailed level than with older techniques, making them less processor intensive. And this makes them ideal for on-device or cloud use. After Google analyzes your image, it may apply its somewhat counter-intuitive methods to reduce blur and noise.
These are counter-intuitive because they push your photo in the apparently ‘wrong’ direction before bringing it back to an improvement over the original. To reduce noise, Google combines pixels with noise (effectively downsampling the image) and then merges them together while regenerating finer details. The sharpening works in a similar way, with Google’s algorithms re-blurring the image multiple times in an efficient, phone-friendly process.
So how does Photo Unblur build on these techniques? We don’t know the details at this point, but a year is a long time in machine learning – and some samples from Google during the Pixel 7 launch certainly looked impressive.
For example, the image below has been impressively cleaned up from its nearly useless origin, which appears to have been caused by light movement and too long a shutter speed.
Because Photo Unblur doesn’t work with two images of the same scene, like Face Unblur, it can struggle to be as powerful as that older feature, especially for issues caused by motion. But we’re looking forward to giving our old snaps a try when the Pixel 7 and Pixel 7 Pro launch.
How do you use Photo Unblur?
Google has again not revealed the details of how to use Photo Unblur on the Pixel 7 and Pixel 7 Pro. But it has said that with “just a few taps” you’ll be able to remove blur and visual noise in a process that sounds as simple as last year’s Magic Eraser (for removing unwanted objects).
This process takes place in the Google Photos app, with Photo Unblur initially only available on the PIxel 7 and Pixel 7 Pro. But we expect the technology to be available on all devices running the Google Photos app at a later date.
While Photo Unblur isn’t as automated as Face Unblur, which works while taking photos on phones from the Pixel 6 series, it looks like another very simple example of computational photography that enhances our snaps. Including the old one we had written off.
It seems the two modes are complementary, with Face Unblur being activated (on supported devices) before you take a photo, and Photo Unblur being useful for old photos taken with a camera. We’ll be giving Photo Unblur a try soon and will update this article with all our findings.