Skip to main content

Beyond Portrait Mode … next-generation computational photography technique demonstrated [Video]

A former Google SVP recently praised Apple’s use of computational photography to achieve shallow depth of field shots with the dual camera on the iPhone 7 Plus. A research team has now developed a next-generation computational photography technique that allows you change the perspective of a photograph after it has been taken – including achieving effects not possible with conventional cameras …

The research paper was spotted by DPReview.

Researchers with the University of California, Santa Barbara (UCSB) and NVIDIA have detailed a new type of technology called ‘computational zoom’ that can be used to adjust the focal length and perspective of an image after it has been taken […]

According to UCSB, computational zoom technology can, at times, allow for the creation of ‘novel image compositions’ that can’t be captured using a physical camera. One example is the generation of multi-perspective images featuring elements from photos taken using a telephoto lens and a wide-angle lens.

For example, there may be times when you want to take a photo of a person in front of an impressive building or other close-up structure. With conventional photography, you either need to get a long way back – which leaves the person a small element in the photo – or use a wide-angle lens, which distorts the person (in very unflattering ways!).

With the technique described here, a range of different photos can be combined in ways that effectively apply different focal lengths to different elements of the photo. For example, the building (or rollercoaster in the example shown below) can have a short focal length that shows the whole thing, while the person in front of it has a long focal length that leaves them looking as they do in real life.

The approach isn’t as simple as Portrait Mode, where the iPhone 7 Plus takes one photo with each lens and uses parallax to work out depth before applying an artificial blur to the background. Computational zoom requires you to take a number of separate photos from different places, but that’s not to say that a future iPhone equipped with more than two cameras couldn’t do the same thing with what amounts to a single shot.

Via The Verge

FTC: We use income earning auto affiliate links. More.

You’re reading 9to5Mac — experts who break news about Apple and its surrounding ecosystem, day after day. Be sure to check out our homepage for all the latest news, and follow 9to5Mac on Twitter, Facebook, and LinkedIn to stay in the loop. Don’t know where to start? Check out our exclusive stories, reviews, how-tos, and subscribe to our YouTube channel



Avatar for Ben Lovejoy Ben Lovejoy

Ben Lovejoy is a British technology writer and EU Editor for 9to5Mac. He’s known for his op-eds and diary pieces, exploring his experience of Apple products over time, for a more rounded review. He also writes fiction, with two technothriller novels, a couple of SF shorts and a rom-com!

Ben Lovejoy's favorite gear