Adobe Photoshop Uses AI to Increase Image Pixels by Four Times
Adobe is bringing Super Resolution to Photoshop, using artificial intelligence to increase an image’s pixels by four times.
Everyone has seen a TV show where the character says those two infamous words: “Zoom in.” As anyone who’s actually worked with digital photos can attest, any photo magnifying is limited by the size and quality of the image. If a picture doesn’t have the necessary pixel density, it can only be enlarged so much before it becomes pixilated and loses its clarity.
Beyond being an inaccurate staple of virtually every police procedural, there are a number of practical situations where this can be a limitation. Printing a photo taken with a low-resolution camera is a perfect example, as it takes a higher resolution photo to look good when printed.
“Super Resolution is also a pixels project, but of a different kind,” writes Adobe’s Eric Chan. “Imagine turning a 10-megapixel photo into a 40-megapixel photo. Imagine upsizing an old photo taken with a low-res camera for a large print. Imagine having an advanced ‘digital zoom’ feature to enlarge your subject. There’s more goodness to imagine, but we’re getting ahead of ourselves. To understand Super Resolution properly, we must first talk about Enhance Details.”
Super Resolution uses AI to intelligently expand a photo, keeping it crisp with minimal artifacts.
“The term ‘Super Resolution’ refers to the process of improving the quality of a photo by boosting its apparent resolution,” continues Chan. “Enlarging a photo often produces blurry details, but Super Resolution has an ace up its sleeve — an advanced machine learning model trained on millions of photos. Backed by this vast training set, Super Resolution can intelligently enlarge photos while maintaining clean edges and preserving important details.”
Super Resolution is now available in Camera Raw 13.2 and will soon be included in Lightroom and Lightroom Classic.