--In this contribution, we introduce the concept of Instance Performance Difference (IPD), a metric designed to measure the gap in performance that a robotics perception task experiences when working with real vs. By pairing synthetic and real instances in the pictures and evaluating their performance similarity using perception algorithms, IPD provides a targeted metric that closely aligns with the needs of real-world applications. We explain and demonstrate this metric through a rock detection task in lunar terrain images, highlighting the IPD's effectiveness in identifying the most realistic image synthesis method. The metric is thus instrumental in creating synthetic image datasets that perform in perception tasks like real-world photo counterparts. In turn, this supports robust sim-to-real transfer for perception algorithms in real-world robotics applications.

This contribution reports on a software framework that uses physically-based rendering to simulate camera operation in lunar conditions. The focus is on generating synthetic images qualitatively similar to those produced by an actual camera operating on a vehicle traversing and/or actively interacting with lunar terrain, e.g., for construction operations. The highlights of this simulator are its ability to capture (i) light transport in lunar conditions and (ii) artifacts related to the vehicle-terrain interaction, which might include dust formation and transport. The simulation infrastructure is built within an in-house developed physics engine called Chrono, which simulates the dynamics of the deformable terrain-vehicle interaction, as well as fallout of this interaction. The Chrono::Sensor camera model draws on ray tracing and Hapke Photometric Functions. We analyze the performance of the simulator using two virtual experiments featuring digital twins of NASA's VIPER rover navigating a lunar environment, and of the NASA's RASSOR excavator engaged into a digging operation. The sensor simulation solution presented can be used for the design and testing of perception algorithms, or as a component of in-silico experiments that pertain to large lunar operations, e.g., traversability, construction tasks.

For about two years, the 38-year-old globe-trotting photographer had been mulling over the "surreal photo of an already surreal-looking type of bird" he had shot in the pristine beach off the coast of Aruba. That sunny day, Astray had left around 5 a.m. on the first boat bound to the tiny island known for its flock of flamingos, hoping to beat the crowds. When he got there, he spotted a bright pink bird "doing its morning routine" and cleaning its feathers, he said. The "very lucky shot" captured the flamingo mid-belly scratch.

It's the fast-growing technology that continues to fool millions of social media users around the world - but how adept are YOU at spotting a fake AI photo? From the Pope posing in a puffer coat to Donald Trump being arrested on the streets of New York, images created by artificial intelligence are becoming increasingly convincing. While some of the snaps are clearly fake and designed to amuse or make a political statement, there are experts who fear the technology's potential as a weapon of mass disinformation. It comes as a German artist who won the Sony World Photography Award this week refused to accept his prize after revealing his black and white portrait of two women was in fact created by AI. Boris Eldagsen tricked competition organisers with his entry, Pseudomnesia: The Electrician - a haunting close-up of two women in a grainy sepia which won the creative open category.

Software enables completely new inspiration in the creative process By keeping AI software development entirely in-house, Audi demonstrates competence in a crucial emerging field Leveraging artificial intelligence (AI) in all departments: this is the goal Audi has set itself on its way to becoming a data-driven company. With FelGAN, the company now employs software that uses artificial intelligence to open up new sources of inspiration for designers. Creative people are always on the lookout for inspiration. The same is true of the designers who create new wheels at the Audi Design Studio in Ingolstadt. But where to find untapped sources of inspiration?

My denim bikini has been replaced with exposed, pale pink nipples – and a smooth, hairless crotch. I zoom in on the image, attempting to gauge what, if anything, could reveal the truth behind it. There's the slight pixilation around part of my waist, but that could be easily fixed with amateur Photoshopping. Although the image isn't exactly what I see staring back at me in the mirror in real life, it's not a million miles away either. And hauntingly, it would take just two clicks of a button for someone to attach it to an email, post it on Twitter or mass distribute it to all of my contacts. Or upload it onto a porn site, leaving me spending the rest of my life fearful that every new person I meet has seen me naked. Because this image, despite looking realistic, is a fake.

Computers have become very, very good at generating photorealistic images of human faces. What could possibly go wrong? A study published last week in the academic journal Proceedings of the National Academy of Sciences confirms just how convincing "faces" produced by artificial intelligence can be. In that study, more than 300 research participants were asked to determine whether a supplied image was a photo of a real person or a fake generated by an A.I. The human participants got it right less than half the time.

Many machine learning classifiers are vulnerable to adversarial attacks, inputs with perturbations designed to intentionally trigger misclassification. Modern adversarial methods either directly alter pixel colors, or "paint" colors onto a 3D shapes. We propose novel adversarial attacks that directly alter the geometry of 3D objects and/or manipulate the lighting in a virtual scene. We leverage a novel differentiable renderer that is efficient to evaluate and analytically differentiate. Our renderer generates images realistic enough for correct classification by common pre-trained models, and we use it to design physical adversarial examples that consistently fool these models. We conduct qualitative and quantitate experiments to validate our adversarial geometry and adversarial lighting attack capabilities.

Thanks to the modern gaming industry, we can now spend our evenings wandering around photorealistic game worlds, like the post-apocalyptic Boston of Fallout 4 or Grand Theft Auto V's Los Santos, instead of doing things like "seeing people" and "engaging in human interaction of any kind." Games these days are so realistic, in fact, that artificial intelligence researchers are using them to teach computers how to recognize objects in real life. Not only that, but commercial video games could kick artificial intelligence research into high gear by dramatically lessening the time and money required to train AI. "If you go back to the original Doom, the walls all look exactly the same and it's very easy to predict what a wall looks like, given that data," said Mark Schmidt, a computer science professor at the University of British Columbia (UBC). "But if you go into the real world, where every wall looks different, it might not work anymore." Schmidt works with machine learning, a technique that allows computers to "train" on a large set of labelled data--photographs of streets, for example--so that when let loose in the real world, they can recognize, or "predict," what they're looking at.