We’ve seen some interesting uses of AI so far, and the latest prototype software launched by Nvidia could be of great help to many artists. It can turn your crude sketches into pretty realistic landscapes in a matter of a click.
colourise.sg the best AI-based colorizing tool so far
We have seen several AI-based colorizing tools so far, and colourise.sg is the latest addition to this bunch. While some other services like Algorithmia still need to improve, colourise.sg is capable of doing a fantastic job in only a matter of seconds.
Skylum is releasing an AI-powered imaging app designed specifically for drones
Skylum is no stranger to AI-powered imaging apps. Luminar and Aurora HDR both feature AI-enhanced effects to help make your post-processing life a little easier, and their Photolemur software is entirely AI-based. Now, Skylum is turning their attention towards drone photographs with a new desktop app for Windows and Mac called AirMagic.
Adobe Lightroom and Camera Raw now use AI to enhance details in your photos
Adobe has been using its AI-powered Sensei technology to introduce various upgrades to its apps. In the most recent upgrade, Camera Raw, Lightroom Classic, and Lightroom CC became able to enhance details in your images and give you up to 30% higher resolution on raw files.
Photographer reveals what it’s like to photograph a humanoid robot
You might well have heard of Sophia, a humanoid robot built by Hong Kong-based company Hanson Robotics. Although she’s not a human, she resembles one in more than just facial features. She interacts with people, she can reportedly recognize faces, and she can mimic 62 human facial expressions. So how do you photograph something (or someone) that so closely resembles a human, yet isn’t actually a real human?
Italian-born photographer Giulio Di Sturco had a chance to take portraits of this humanoid robot and her expressive silicone face. But even more than that: he was granted exclusive permission to explore the story behind Sophia and the lab where she was made.
The Obsbot Tail uses an AI powered camera to produce perfect selfie videos
The concept of a camera that can follow a subject all by itself isn’t a new idea. Well, I say all by “itself”, the camera was usually paired with some kind of “homing device” on the wearer to tell the camera in which direction to point. But the Obsbot Tail needs no homing device. It uses AI tracking to follow a subject automatically, even if visual line of sight is broken.
These AI-powered cameras help to protect endangered African wildlife
Artificial intelligence is already used in cameras for various purposes, but Resolve and Intel have teamed up and created an AI-based camera that is used for a good cause. Their TrailGuard is a camera that helps to protect endangered species in Africa. It’s able to detect, stop, and arrest poachers before it’s too late.
These portraits are entirely AI-generated, these people are not real
We’ve seen NVIDIA’s impressive content aware tool and noise removing tool. They have recently developed a generative adversarial network (GAN) which easily customizes styles of realistic faces and creates new faces. That’s right, these super-realistic faces you can see in the lead image are not real at all!
Xiaomi’s new AI fixes image exposure and detail in low-quality photos
Chinese company Xiaomi is working on an algorithm that will improve low-quality images. The company wants to compete with Apple regarding smartphone photography, and it has just published a new paper on the AI network called “DeepExposure.” It uses machine learning to improve low-quality images by adding them detail while enhancing colors and brightness.
Google used this crazy 5-phone case to tweak Portrait Mode on the Pixel 3
When the Google Pixel 2 came out it was extremely impressive. Despite only having the single rear camera, it beat out everything else on DxOMark and held the position for quite a while. When the Pixel 3 was announced, it also had only the single rear camera. And despite one or two issues with the phone overall, Google made some great improvements with it.
Google has published a blog post on how they taught the Pixel 3 to predict depth for its Portrait Mode. Given that it only has a single camera, and not the dual cameras of other brands, it seems like it wouldn’t be possible, but the techniques used are pretty interesting. And involve a case that holds five separate cameras.
- 1
- 2
- 3
- …
- 6
- Next Page »
