There are plenty of existing methods for digitizing printed photos, and most of them fall on a spectrum between ‘arduous with good results’ and ‘quick with terrible results.’ Google’s new PhotoScan app aims to aims to bridge the gap with a method that’s easy and produces good results by employing computational photography.
The free app, available now for Android and iOS, requires the user to place their photo on a flat surface. After snapping a reference frame, the app directs the user to move their phone around the image to capture more data and, critically, move around the glare that the photo is almost certainly reflecting.
After you’ve made a successful pass, the app will work its magic and spit out a digitized, glare-free rendition of your photo. Images can be saved to your phone’s camera roll and to the cloud. In less than a minute, you’ve got a shareable digital photo that’s way better than the quick-and-dirty version.
Decent scans of instant photos with minimal effort? Sign me up. I scanned these Instax prints with Google’s PhotoScan app and they are gloriously glare-free.
The app analyzes your photo and identifies reference points so it can merge multiple versions of the same image, and compares pixel-level details to judge which image is free of glare. It’s based on technology Google and MIT have been developing to help remove unwanted reflections and obstructions from photos.
The app automatically crops, straightens and rotates your photo, but you can rotate and adjust the corners after capture if needed. My first few tries show surprisingly good results, with glare nearly totally removed in each image. The app uses your phone’s flash to provide illumination, but even so, using better available light produced the nicest results. The results look good enough for social sharing, but if it’s high resolution, high quality digital conversions you’re after, you’ll probably still need to go about it the hard way.
For more information you can watch Google’s Nat and Lo interview researchers about how it all works.