Wonderful stuff. First, from the Google Research Labs:
Enhance! RAISR Sharp Images with Machine Learning
Everyday the web is used to share and store millions of pictures, enabling one to explore the world, research new topics of interest, or even share a vacation with friends and family. However, many of these images are either limited by the resolution of the device used to take the picture, or purposely degraded in order to accommodate the constraints of cell phones, tablets, or the networks to which they are connected. With the ubiquity of high-resolution displays for home and mobile devices, the demand for high-quality versions of low-resolution images, quickly viewable and shareable from a wide variety of devices, has never been greater.
With “RAISR: Rapid and Accurate Image Super-Resolution”, we introduce a technique that incorporates machine learning in order to produce high-quality versions of low-resolution images. RAISR produces results that are comparable to or better than the currently available super-resolution methods, and does so roughly 10 to 100 times faster, allowing it to be run on a typical mobile device in real-time. Furthermore, our technique is able to avoid recreating the aliasing artifacts that may exist in the lower resolution image.
They have a couple before and after photos at the site - the results are quite good.
Second - from Digital Photography Review:
Google's new PhotoScan app makes digitizing prints super easy
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.
Brilliant idea - take a baseline photo and then use a video to analyse where the glare and shadows are plus harvest more pixels. Very clever!
Leave a comment