A team of researchers at Google has come up with really awesome use of all those photos of popular tourist spots. They’ve created an algorithm that takes those photos and turns them into realistic and very detailed 3D renderings. And the best of all is that it even edits out interfering objects and evens out the changes in lighting.
Facebook introduced 3D photos back in 2018, allowing your photos to appear as if they had depth and “move” accordingly as you scroll. This interesting feature has been available only to phones with multiple cameras – until now. Thanks to AI, Facebook is now unrolling this feature to many more users. From now on, you’ll be able to turn any 2D photo into 3D, even your old pictures.
About three days ago, we started seeing a new gimmick on Facebook, images that appear to “move in 3D” when you scroll through them or move your mouse cursor over them. This is a parallax effect and it can be accomplished by providing Facebook with a depth map (e.g. “arches_depth.png”) along with the original image (“arches.png”). The two need to have the same resolution and the depth map needs to be generated in a way that close objects are white and far away objects are black.
You know those Facebook photos where you move your phone or your mouse and they move. Kinda like making you feel you are in the photo? Well, Unmesh Dinda totally nails it in explaining to to create those photo directly from your PC (ok, ok, or Mac) and upload them to photoshop.
The trick is done using depth maps. And as you may guess, those are maps that tell Facebook what is the depth of each part in the photo.
After announcing 3D photos and VR memories back in May, Facebook is now rolling out the feature that can turn your 2D photos into 3D. The new feature will work both in the News Feed and VR. The technology captures the distance between the subject and the background, so it brings scenes of 2D photos to life with 3D depth and movement.
The release of RED’s new Hydrogen One holographic smartphone is drawing ever closer. We’ve known about its modular connectivity through the pogo pins on the back, but very little has been said about what they’re for. It’s been suggested that we’d perhaps see battery packs or small camera modules to use “real” lenses and that it may offer communication with RED’s range of cameras.
Well, the first of those cameras has been announced. RED has teamed up with a 3D VR camera company, Lucid on an 8K prosumer 3D camera. A camera not only shoots holographic content that can be viewed on the Hydrogen One but a camera which also uses the Hydrogen One as its “viewfinder” while shooting.
We’ve all seen an assortment of 360-degree cameras in the past few years, but I have to say that QooCam‘s design is the most intriguing. Just imagine being able to switch from 4K 360 to 3D 180 by simply twisting it? Furthermore, it also features a depth-sensing technology that allows you to refocus after taking a photo. It appears to be quite a capable for a camera that’s slightly longer than an iPhone.
Well, this is pretty cool, a pair of new 3D 180° VR cameras, developed in partnership with Google for their VR180 app. They’re kicking the new VR180 platform with two offerings from Lenovo and YI Technology. While the hardware is similar to a 360° camera, the configuration makes the final result very different. Instead of having one lens facing forward and one facing back, two stare in the same direction side-by-side.
This setup allows for 180-degree stereoscopic 3D video or stills when viewed back on Google Cardboard or a VR headset. The first camera is the Lenovo Mirage, which has a pair of 13 megapixel fisheye lenses with 4K sensors. Likewise, the YI VR180 also houses a pair of lenses and sensors, but is capable of 16.6MP images and 5.7K video.
Creating a 3D model of someone’s face usually requires multiple shots taken from different angles. But researchers from the University of Nottingham and Kingston University have created an AI tool that makes it from a single portrait photo.
The scientists describe the 3D face reconstruction as a “problem of extraordinary difficulty.” However, they’ve managed to use neural networks to turn any 2D portrait into a 3D model. There’s also a free online demo for you to try it yourself.