Discover the experience for yourself with these QR Codes by downloading the Aero app. We recommend running the experience for iOS on 8S and above, or on Android, Private Beta, US only, a list of Android can be found here on HelpX. (FYI, the experience may take a few seconds to load as it is a more sophisticated AR project.)
I love hearing creators—especially obsessive ones like Denis Villenueve—discussing the details of their craft. Here the director takes us inside the making of one of Dune’s most memorable scenes:
We use the lockdown for projects that we have always wanted to implement when there are no visitors. This week we broke the world record. A locomotive drives 220 meters of track through the entire Wunderland and strikes several thousand glasses, while playing a medley of well-known classical songs.
“Ireland invites giant screen audiences on a joyful adventure into the Emerald Isle’s immense natural beauty, rich history, language, music and arts. Amid such awe-inspiring locations as Giant’s Causeway, Skellig Michael and the Cliffs of Moher, the film follows Irish writer Manchán Magan on his quest to reconnect Irish people from around the world with their land, language, and heritage.
Of course, my wry Irishness compels me to share Conan O’Brien’s classic counterpoint from the blustery Cliffs of Moher…
This new witchcraft “synthesizes not only high-resolution, multi-view-consistent images in real time, but also produces high-quality 3D geometry.” Plus it makes a literally dizzying array of gatos!
Unsupervised generation of high-quality multi-view-consistent images and 3D shapes using only collections of single-view 2D photographs has been a long-standing challenge. Existing 3D GANs are either compute-intensive or make approximations that are not 3D-consistent; the former limits quality and resolution of the generated images and the latter adversely affects multi-view consistency and shape quality. In this work, we improve the computational efficiency and image quality of 3D GANs without overly relying on these approximations. For this purpose, we introduce an expressive hybrid explicit-implicit network architecture that, together with other design choices, synthesizes not only high-resolution multi-view-consistent images in real time but also produces high-quality 3D geometry. By decoupling feature generation and neural rendering, our framework is able to leverage state-of-the-art 2D CNN generators, such as StyleGAN2, and inherit their efficiency and expressiveness. We demonstrate state-of-the-art 3D-aware synthesis with FFHQ and AFHQ Cats, among other experiments.
I like this concise 6-minute list from Shutterstock, though I wish they touched on how to avoid the dreaded scourge of propeller shadows. (Somehow I’ve yet to look this up & get my head conclusively around it.)
“With the power of Facebook’s massive database, your personal Mark Zuckerberg knows absolutely everything. Zuck on a Truck can tell if you’ve been naughty or nice. He knows every website you’ve ever visited, every place you’ve ever lived, every friend you’ve ever made, every love you’ve ever lost, every schoolmate you’ve stalked — Zuck on a Truck even knows when you’ll die!”
The whole thing rapidly darkens as FB connects all the naughty children to take down democracy—while all the while taking no responsibility:
The imagineers (are they still called that?) promise a new way to create photorealistic full-head portrait renders from captured data without the need for artist intervention.
Our method begins with traditional face rendering, where the skin is rendered with the desired appearance, expression, viewpoint, and illumination. These skin renders are then projected into the latent space of a pre-trained neural network that can generate arbitrary photo-real face images (StyleGAN2).
The result is a sequence of realistic face images that match the identity and appearance of the 3D character at the skin level, but is completed naturally with synthesized hair, eyes, inner mouth and surroundings.