"Multimodal AI" is suddenly everywhere, with companies like Meta, OpenAI, Google, and Microsoft all using the term to sell people on new AI models and services in just the past few weeks. But what is "multimodal," and what does it mean?
A new tool created by a team at the University of Chicago can add undetectable pixels to images to help creatives protect their work from AI image generators by effectively poisoning (corrupting) the AI's training data.
A group of scientists has developed a battery-free, wireless underwater camera that is powered by sound and is around 100,000 times more energy-efficient than other undersea cameras.
A team of researchers has developed an artificial vision system that offers a full, panoramic view both above and under the water that is inspired by the eyes of fiddler crabs.
Engineers from the Massachusetts Institute of Technology (MIT) have created a stamp-sized sticker that can provide live, high-resolution ultrasound images of the heart, lungs, and other internal organs.
Engineers at the Massachusetts Institute of Technology (MIT) have repurposed a 19th-century photography technique to create an elastic material that changes color when it is stretched.
A team of scientists has created an algorithm that can label objects in a photograph with single-pixel accuracy without human supervision.
Inspired by do-it-yourself camera parts and projects, Ping-Hsun Chen and Ruha Cheng took things a step further and released a retro-style RUHAcam kit built around a Raspberry Pi Zero W connected to the High-Quality Camera Module.
Using physical glass elements for camera lenses has been at the core of imaging technology for centuries, but MIT engineers have now fabricated a new "metalens" that can focus on objects at multiple depths without changing its physical position or shape.
A team of engineers at MIT and the University of Massachusetts at Lowell have created something that, on the surface, seems impossible: they've designed a 180° fisheye lens from a single, 1mm-thin piece of calcium fluoride glass that is completely flat.
There's amazing work being done in the area of using neural networks to edit or create photos. If you'd like to experience some cutting-edge technology for yourself, check out GANPaint Studio. It's a free online demo that shows how photo editing tools of the future could work.
A team of researchers at MIT have created a new AI algorithm that can help cameras "see" off-camera things using only moving shadows.
In a breakthrough that seems more science fiction than science fact, researchers at MIT have developed a model that can recover "lost dimensions" in images. Translation: it can recreate video from a motion-blurred photograph, and may some day be able to create a 3D scan from a 2D image.
What if your camera could professionally retouch your photos... before you even shoot them? That's what researchers at Google and MIT are currently working on.
In their work with ETH Zurich, MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL) have developed a drone that simplifies aerial tracking by removing humans almost entirely from the equation.
A trio of scientists from MIT's Media Lab decided to get creative for Halloween ... and just maybe scare the pants off of you. So if you're wondering how Kermit turned into undead Kermit, meet the aptly-named 'Nightmare Machine.'
Researchers in MIT's Computer Science and Artificial Intelligence Laboratory are quite literally letting you reach in and touch pieces of an image using just a few seconds of video and their "Interactive Dynamic Video" technology.
There are no real images of a black hole, only artist renderings like the one above and that really cool CGI version in the movie Interstellar. But that may change in the coming years thanks to an algorithm recently developed at MIT.
Some photographs have the power to burn themselves into our memories for a long time, while others are easily forgettable after they're seen. Scientists are MIT have been researching the science behind memorable images, and now they've created a web app called LaMem that can analyze any photo and assign it a memorability score.
MIT scientists have designed a new camera that will never overexpose a photograph, no matter what the lighting situation is. Called a "modulo camera," it captures a high dynamic range photo with every exposure.
Researchers at Google and MIT have figured out a way to automatically remove reflections and obstructions from photographs, and their latest demo of the technology is amazing.
Check out the 6.5-minute video above for an explanation of the algorithm and some examples of what it can do.
Photographers often use products such as the Lens Skirt when shooting through windows in order to reduce or remove reflections. Thanks to advances in computer algorithms, those physical tricks may soon find themselves alongside suitable software solutions.
Scientists at MIT have created an algorithm that can automatically remove reflections from photos that were taken through windows.
It’s not unusual for colleges with large open-source programs to put out a number of courses free for the world to browse through online. In the past we’ve featured courses from both MIT and Stanford.
A group of researchers from MIT want your next lighting rig to be autonomous and airborne. Set to be on display this August at the Symposium on Computational Aesthetics in Graphics, Visualization and Imaging, they've actually developed a drone that automatically and dynamically lights a subject (living or otherwise) for a photographer while he or she focuses on getting the shot.
Are you not impressed with your average Instagram selfie? Is the lighting too bland and out of place for your liking? If so, a team made up of a researcher from MIT and a few individuals from Adobe and the University of Virginia might just have a solution to your problem.
They’ve created an algorithm capable of accurately stylizing an average, otherwise insignificant selfie to look like the works of some of the best-known and well-respected portrait photographers of all time.
A photographer's primary concern when taking a photo might not be "I wonder how many likes this will get," but being able to gauge popularity could still come in handy when you're trying to decide which photos to upload to your favorite sharing site.
Enter MIT PhD candidate Aditya Khosla and his new algorithm that does just that: tells you how popular your photos will be before you even upload them.
A super-fast, affordable new camera currently under development at MIT could improve everything from video game experiences to driving safety, researchers reported at a recent tech convention.
Can you trust camera reviews submitted by customers of online retailers? Not entirely, suggests a new academic study, and not for the reasons you might think.
The majority of in-camera editing and enhancing, especially on the mobile front, is done via software. Software that, according to MIT's Rahul Rithe, "consume[s] substantial power, take[s] a considerable amount of time to run, and require[s] a fair amount of knowledge on the part of the user."
In order to bypass this problem, Rithe and his team of researchers at MIT have developed a new imaging chip that can act as a photographic "jack of all trades" when it comes to taking your smartphone photos to the next level.
"Any sufficiently advanced technology is indistinguishable from magic." That's the quote by science fiction author Arthur C. Clarke that you'll find on Cardiio's homepage. It's a quote that is quite appropriate, given what the app can do.
The app is a touch-free heart rate monitor that can accurately tell you your pulse by simply looking at your face through your phone's camera.