Medium: How to recognize fake AI-generated images. “Here are some things you can look for when trying to recognize an image produced by a GAN [generative adversarial network]. We’ll focus on faces because they are a common testing ground for researchers, and many of the artifacts most visible in faces also appear in other kinds of images.”
images
MakeUseOf: What Could Robots Do With Your Pictures? 5 Cool AI-Based Photo Editing Apps
MakeUseOf: What Could Robots Do With Your Pictures? 5 Cool AI-Based Photo Editing Apps. “There’s a curiosity around AI that is difficult to quench. So far, we’ve seen how neural networks create paintings, but AI is now going beyond that. There are apps that are trying to ‘see’ photos the way a human would, and do useful or fun stuff based on it.”
Make Tech Easier: 5 Useful Tools For Batch-Editing Images in Windows
Make Tech Easier: 5 Useful Tools For Batch-Editing Images in Windows. “Sometimes you just have a whole mountain of images you need to edit. Perhaps you need them all at a specific size or want them all to follow a specific naming convention. Before you open them all and edit them one by one in your favorite image-manipulation program, perhaps consider a batch-editing program to do all the hard work for you. If you have a lot of photos to clear and little patience to offer, these handy tools will make life that little bit easier!”
MIT Technology Review: AI software can dream up an entire digital world from a simple sketch
MIT Technology Review: AI software can dream up an entire digital world from a simple sketch. “Creating a virtual environment that looks realistic takes time and skill. The details have to be hand-crafted using a graphics chip that renders 3D shapes, appropriate lighting, and textures. The latest blockbuster video game, Red Dead Redemption 2, for example, took a team of around 1000 developers more than eight years to create—occasionally working 100-hour weeks. That kind of workload might not be required for much longer. A powerful new AI algorithm can dream up the photorealistic details of a scene on the fly.”
Gizmodo: Google’s ‘Inception’ Neural Network Tricked By Images Resembling Bad Video Games
Gizmodo: Google’s ‘Inception’ Neural Network Tricked By Images Resembling Bad Video Games. “Neural networks can do some impressive stuff these days, from generating photorealistic faces to writing short films. Image recognition is another hot area, with projects such as Google Inception leading the way in accuracy. Even so, it still has a long way to go, as researchers from Auburn University and Adobe have revealed in a new paper.”
New York Times: It’s Almost 2019. Do You Know Where Your Photos Are?
New York Times: It’s Almost 2019. Do You Know Where Your Photos Are?. “Do you know where your photos are? Most of us don’t, at least not exactly, or in terms that we fully understand. Holding on to pictures was, for most of the history of photography, a matter of material decay and physical storage. Are these prints fading, and how fast? Are they organized by year or by subject? Do I know where they are? To the people who took them, they were deeply valuable; to anyone else, mostly worthless. Their peculiar sort of pricelessness made archivists of regular people.”
MakeUseOf: Instagram Can Now Describe Photos to Visually Impaired Users
MakeUseOf: Instagram Can Now Describe Photos to Visually Impaired Users. “Instagram has added two new features designed to make it easier for visually impaired people to use Instagram. These features mean screen readers will be able to accurately describe what’s in photos uploaded to Instagram.”
