Hacking Photography - one Picture at a time
Deepfakes have been a thing for a while now, and they’ve been used for fun, useful, but also malicious purposes. Samsung has now introduced yet another deepfake tool that turns a single still image into a creepily accurate video.
Samsung’s Megapixel portraits, or MegaPortraits, is able to create high-resolution human avatars. All it needs is a single portrait, and it doesn’t even have to be a photo – you can also turn paintings into moving portraits, for some extra creepiness.
There are now two ways of creating digital images with a camera. You can either follow a software-centric computational photography approach. The other way is to stick to traditional hardware-centric optical photography. The former is used with AI to help enhance the final image, the latter relies on the quality of the camera’s components (e.g. lens, sensor). The two techniques may differ, but they are not at all on a collision course. They can complement each other and even address each technique’s limitations.
Sony has announced that they’ve established a new “Sony AI” organisation, with offices in Japan, Europe and the USA. Its goal is to advance the research and development of AI. They see AI playing a vital role in the future, particularly when it comes to imaging & sensing, robotics and entertainment.
Their purpose, Sony says is to “Fill the world with emotion, through the power of creativity and technology” and that AI will play a big part in that. Sony AI will drive the R&D of AI through “multiple world-class flagship projects”, and they’ll be looking into the ethics of AI technology, too.
Deepfake has become a pretty hot topic in the world of visual AI over the last couple of years, and it’s come a very long way in a short amount of time. It’s an incredible and terrifying technology. And now Samsung has jumped on the bandwagon.
Researchers at the Samsung AI Center in Mosci and the Skolkovo Institute of Science and Technology have published a new paper detailing their new software that generates 3D animated heads from a still image. And while it’s not perfect, to be able to do this from a handful or even a single image is pretty mindblowing.
Computational imaging has given us some interesting and useful inventions so far, from fake bokeh to capturing the movement of light. This time, scientists have figured out how to take a clear image from as far as 28 miles (45km), regardless of the Earth’s curvature and the amount of smog in the air.
Light, the company behind the Light L16 camera which contains 16 sensors and lenses, has announced that they’ve teamed up with Sony to create the next generation of multi-camera smartphones. Well, we knew Light was working on something to do with phones, and now it looks like it’s official.
Google Pixel 3 may only have one rear camera, but it relies heavily on Google’s promising AI to deliver high-quality images. The latest feature Google launched for all three generations of Pixel lets you shoot clean and bright images in near darkness – even when you can barely see anything with your own eyes. It works on both front and rear cameras, and you don’t even need a tripod or a flash.
Google, it seems, is acquiring Lytro. Yes, the company that made that crazy light field camera and then got out of photography to move into VR and cinema is being snapped up. In a deal which TechCrunch report to be worth either $40mil or $25mil, depending on who you ask, Google will pick up the company in an “asset sale”. Presumably, this will include the 59 patents related to light-field and imaging technology which Lytro owns.
This whole “computational photography” thing always felt a little bit weird. But it also intrigued me. The idea that a computer can realistically create things that weren’t actually shown in the original shot is pretty amazing. Maybe it was seeing this scene in Blade Runner as a kid that did it for me. It was pure fantasy back then, but we’re getting there.
A new “computational zoom” technology developed by researchers at Nvidia and UCSB brings us a step closer to Deckard’s reality. Essentially it allows the photographer to change the focal length and perspective of an image in post, but this description barely does it justice. It actually allows you to simulate multiple focal lengths simultaneously. Here, watch this video, and it’ll all make sense.
At just 200 microns in diameter, this may very well be the smallest camera in the world. Patrick Gill, a senior research scientist for a technology licensing company named Rambus, has developed a camera sensor that can capture pictures while still retaining a near-microscopic size.
FIND THIS INTERESTING? SHARE IT WITH YOUR FRIENDS!