deeplearning

Researchers believe they have eliminated the problem of camera operators appearing in shot during live sports games.

Canon has showcased a neural network, deep learning-powered image processing technology that can dramatically improve image quality in three areas: noise, color, and lens imperfections such as aberrations or blur.

Nikon has pushed an update for its NX MobileAir smartphone app that adds new JPEG capabilities, support for RAW files, new quality of life features, and a deep learning algorithm for image analysis.

A new technology developed by Panasonic is capable of quickly correcting distortion and tilt from only one image. Using the new method, images shot at an angle or those that are distorted by a wide-angle lens can be instantly corrected.

Sony has announced the Alpha 7R V full-frame camera which features a brand-new AI focusing system. Called Real Time Recognition, this “deep learning” trained system can detect not only humans but also birds, animals, planes, trains, cars, and insects.

Matterport has announced the new Pro3 camera system along with updates to its "digital twin" cloud platform. The Pro3 stands out as it is capable of digitizing every aspect of a physical environment, both inside and outside.

ON1 has announced its next-generation technology that is powered by what it calls state-of-the-art neural networks for image upscaling: Resize AI. The company says it can enlarge photos and create realistic details with spectacular results.

Researchers at the University of Washington have developed a new deep learning method that essentially creates high-quality cinemagraphs automatically. The team says the method can animate any flowing material, including water, smoke, fire, and clouds.

Google has announced updates to its suite of AI-powered features in an effort to make it easier to look back and find meaningful moments and memories while giving better control over what is relived.

Xiaomi today announced the Mi 11 smartphone which houses an impressive new low light technology. Quality nighttime photo-taking capability has been a thing for some time, but this latest device is the world's first to implement a Night Mode for video.

DxO PhotoLab 4 is the company's latest update to its photo editing software powered by a new technology it calls DeepPRIME, a "revolutionary" demosaicing and denoising technology based on artificial intelligence and "trained with deep learning."

Earlier this year, researchers from two universities and Google published a new AI-powered technique they developed called "Depth-Aware Video Frame Interpolation" or DAIN, and it's simply mind-blowing. The tech can interpolate a 30fps video all the way to 120fps or even 480fps with almost no visible artifacts.

Earlier today, Microsoft announced two new tools that will help identify manipulated photos and videos. The first is a metadata-based system, and the second is a "Video Authenticator" that will analyze photos and videos and provide a "confidence score" that tells you whether or not the media has been altered by AI.

In "news we missed last month," genealogy website MyHeritage has launched its very own easy-to-use Photo Enhancer tool that uses deep learning technology to turn blurry or faded family photos into sharp snaps in a single click. People on social media are loving it.

Want to turn your smartphone snapshots into DSLR-quality photos? A group of scientists in Switzerland is trying to help make that possible. They've created a neural network that aims to automatically enhance low-quality phone snapshots into "DSLR-quality photos."

Adobe is teasing an impressive new technology called Scribbler. It's an "interactive deep learning-based image generation system" that you can use to automatically colorize black-and-white photos. Above is a 6.5-minute demo of Scribbler.

The stock photo service Shutterstock has announced a new powerful photo search tool called Composition Aware Search. It uses advanced deep learning technology to let you search for photos containing certain objects in certain locations.

Can machines be trained to create photos that most people would think were shot by a professional human photographer? That's what Google is trying to figure out with a machine learning research project.

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.'

Earlier this week, we showed you some really interesting image editing research from the University of Edinburgh, calling it a peek at the future of Photoshop. Well, it turns out we were more right than we realized.

With over a trillion photos created every year now, one feature that could help people make sense of their massive photo collections could be object recognition and automatic tagging. If your camera and photo management software can figure out what's in your shots, it'll make searching through old photos much more easy and intuitive.

Companies and researchers are working hard on pushing this field forward. Photo sharing services are already adding auto-tagging to their systems -- Flickr and Google had to work out some early "racist" bugs -- and now we're getting a glimpse of what the technology could look like live, in cameras.