For years, production companies have used costly techniques to colorize old black and white movies. But now artificial intelligence is placing that capability in the hands of everyday users, allowing you to add color to old family photos, historical images, or black and white video frames in seconds. It works like this: A developer feeds a large number of color images into a neural network, which is AI-speak for software modeled after brain functions. Over time, the software learns to recognize different objects and determine their likely colors. These algorithms are incorporated into online services as well as software that you can download and run on a computer.
Creative individuals push the boundaries of what's possible. They do this with original ideas and unique perspectives on the world around them. Creatives, more often than not, also rely on advancements in technology to help them bring their visions to life. If you're a photographer, filmmaker, content creator or anyone else who works in visual media, you can take your creativity to new heights with a pair of eyes in the sky. Luckily for you, that's exactly what you get with this roundup of drones.
When photographer Chase Jarvis coined the famous saying "The best camera is the one you have with you," he was revealing an unspoken truth: Even professionals carried point-and-shoot cameras despite owning DSLRs and dedicated video cameras. His message was that great photographers create compelling images with whatever they have on hand, but the sentiment wound up setting the stage for a massive disruption of traditional imaging -- one that saw famed portrait photographer Annie Leibovitz embrace Google's Pixel still cameras and filmmaker Steven Soderbergh start shooting movies with iPhones. The year 2020 will be remembered for many negative reasons, but it should also be marked as the time when technology caught up with and redefined Jarvis' saying. Thanks in large part to improved sensors and the neural cores in mobile processors made by Qualcomm and Apple, this was the year when standalone photo and video cameras were surpassed by smartphones in important ways, such that "the one you have with you" will now actually be either your best or most capable camera. Unlike single-purpose cameras, the latest smartphones now create 3D scans of objects and rooms, AI-optimized images, and cinema-quality Dolby Vision HDR videos that even professional cameras can't replicate.
Photography is more important today than at any other time in recent history. It is used across every space where someone wants to sell you something like services, products, news, and even educational information and programs. The list is never-ending, and photography's demand has led to several photo management innovations- both for the front end and the back end. And this is where recent developments in artificial intelligence and image recognition technology reset to cause a near revolution across the industry. Many modern techniques introduced by AI in photography enhance photography like auto-tagging, suggesting auto-tagging labels your images with appropriate keywords, and are then a part of your image metadata.
Of course a little known facial recognition tool was used on Black Lives Matter protestors. This past June, as protestors were tear-gassed in Washington D.C.'s Lafayette Square so that Donald Trump could have a bible-thumping photo op, officials claim a man assaulted a police officer. The man, Michael Joseph Peterson Jr., wasn't arrested at the scene. Instead, police pulled images off Twitter and ran them through a previously secretive facial recognition system to find a match. So reports the Washington Post, which notes that many experts believe this is the first time a defendant has been told the National Capital Region Facial Recognition Investigative Leads System (NCRFRILS), as it is called, was used to track them down.
"Light," a former camera company has announced a new depth sensor that could be a game changer, upending LIDAR and computer vision based depth measurement, by producing a combination RGB image and depth map with ranges out to an astonishing 1000 meters. Presuming it works as promised and can be delivered at scale, this is astonishing news. Some of you will know Light as a company that made a computational camera with 16 lenses at 3 different focal lengths. Combining the images let them produce a high resolution image with an adjustable depth of field, hoping to get SLR quality in a flat box. The tested their first product, and while interesting, it was not ready for prime-time. They later got money from Softbank.
To snap the photo of your dreams, you might have to get creative. You know, like climbing to the roof, flying over a cityscape, or scaling buildings. Here are 12 drones on sale as of Oct. 31, including drones designed specifically for photography, micro drones, and drones suitable for beginners. The E88 Four-Axis High-Definition Aerial Photography Drone is both lightweight and durable. This drone is on sale for 21% off for a limited time, making it just $59.95.
Over the past year we've heard AI-generated music in the style of Kanye West, Tupac, and Nas, a lyrically nonsensical (but stylistically pretty believable) track based on the catalogue of Travis Scott, and a fake Nirvana song written by a computer. It's not just musicians that are being tapped for inspiration by artificial intelligence though, as confirmed by a recent bot that's learned to create drawings in the style of Banksy. Named GANksy (after the machine learning framework, a generative adversarial network, on which it's based) the software "was born into the cloud" in September 2020, as detailed in a statement on the creator's website. The statement continues to explain that GANksy was trained using hundreds of images from the portfolio of a "certain street artist". And though Banksy isn't explicitly mentioned by name, it seems pretty clear from the title – plus the fact that the images are eerily reminiscent of his work – that he's the artist in question.
Artificial intelligence is quickly becoming an integral part of photo editing software, and Adobe seems to be following the trends. The latest version of Photoshop has been released for desktop and iPad, and it contains an AI-powered feature that lets you tweak your subject's age, gaze, and facial expression in just a few clicks. But there are a few more new AI-based improvements, so let's jump in and see what's new in Photoshop. We have already covered the Sky Replacement feature powered by Adobe Sensei. It separates the sky from the foreground and lets you change the sky in a few clicks, while also tweaking the lighting in the photo so that it matches the new sky.
Perhaps we spoke a tad too soon. Adobe has extended the AI-enhanced capabilities of its Photoshop image editing software to include instant sky replacement, some super-easy selection tools and some early Neural Filters, including emotion editing. It all rolled out today in an update for Creative Cloud subscribers. Probably the most useful to experienced image editors will be the new selection tools, which use Adobe's Sensei AI algorithms to improve the software's ability to quickly draw selection lines around complex objects, in particular where tricky hair, complex backgrounds and objects that blend into the background somewhat. Sky replacement is a very neat feature that does a pretty amazing job of intelligently selecting the sky in your image and dropping in one of a couple dozen standard alternatives – or letting you upload your own sky images to get exactly the look you want.