Lifeboat Foundation

Human-like articulated neural avatars have several uses in telepresence, animation, and visual content production. These neural avatars must be simple to create, simple to animate in new stances and views, capable of rendering in photorealistic picture quality, and simple to relight in novel situations if they are to be widely adopted. Existing techniques frequently use monocular films to teach these neural avatars. While the method permits movement and photorealistic image quality, the synthesized images are constantly constrained by the training video’s lighting conditions. Other studies specifically address the relighting of human avatars. However, they do not provide the user control over the body stance. Additionally, these methods frequently need multiview photos captured in a Light Stage for training, which is only permitted in controlled environments.

Some contemporary techniques seek to relight dynamic human beings in RGB movies. However, they lack control over body posture. They need a brief monocular video clip of the person in their natural location, attire, and body stance to produce an avatar. Only the target novel’s body stance and illumination information are needed for inference. It is difficult to learn relightable neural avatars of active individuals from monocular RGB films captured in unfamiliar surroundings. Here, they introduce the Relightable Articulated Neural Avatar (RANA) technique, which enables photorealistic human animation in any new body posture, perspective, and lighting situation. It first needs to simulate the intricate articulations and geometry of the human body.

The texture, geometry, and illumination information must be separated to enable relighting in new contexts, which is a difficult challenge to tackle from RGB footage. To overcome these difficulties, they first use a statistical human shape model called SMPL+D to extract canonical, coarse geometry, and texture data from the training frames. Then, they suggest a unique convolutional neural network trained on artificial data to exclude the shading information from the coarse texture. They add learnable latent characteristics to the coarse geometry and texture and send them to their proposed neural avatar architecture, which uses two convolutional networks to produce fine normal and albedo maps of the person underneath the goal body posture.

😗

Japan sold a fully-functional robot suit that doesn’t just resemble a combat mech from a video game, it was able to actually fight like one too. With video games like “Armored Core,” mech fans already have a good idea of what giant fighting robots would be like in real life. One such fan is Kogoro Kurata –- an artist who wasn’t satisfied with leaving that notion to the imagination. Kurata explained that driving these giant robots was his dream, saying it was something the “Japanese had to do” (via Reuters). Unlike some of the coolest modern robots available today, Kurata envisioned a full-sized mech he can actually enter and operate: Something he actually accomplished in 2012.

Continue reading “The Japanese Robot Suit That Looks Straight Out Of Armored Core” »

😗

With Qualcomm, Mediatek, and Samsung now sporting ray tracing GPUs, is this the turning point for mobile gaming graphics?

Christopher Nolan revealed to Total Film magazine that he recreated the first nuclear weapon detonation without CGI effects as part of the production for his new movie “Oppenehimer.” The film stars longtime Nolan collaborator Cillian Murphy as J. Robert Oppenheimer, a leading figure of the Manhattan Project and the creation the atomic bomb during World War II. Nolan has always favored practical effects over VFX (he even blew up a real Boeing 747 for “Tenet”), so it’s no surprise he went the practical route when it came time to film a nuclear weapon explosion.

“I think recreating the Trinity test [the first nuclear weapon detonation, in New Mexico] without the use of computer graphics was a huge challenge to take on,” Nolan said. “Andrew Jackson — my visual effects supervisor, I got him on board early on — was looking at how we could do a lot of the visual elements of the film practically, from representing quantum dynamics and quantum physics to the Trinity test itself, to recreating, with my team, Los Alamos up on a mesa in New Mexico in extraordinary weather, a lot of which was needed for the film, in terms of the very harsh conditions out there — there were huge practical challenges.”

Could video streaming be as bad for the climate as driving a car? Calculating Internet’s hidden carbon footprint.

We are used to thinking that going digital means going green. While that is true for some activities — for example, making a video call to the other side of the ocean is better than flying there — the situation is subtler in many other cases. For example, driving a small car to the movie theatre with a friend may have lower carbon emissions than streaming the same movie alone at home.

How do we reach this conclusion? Surprisingly, making these estimates is fairly complicated.

Continue reading “Video streaming as polluting as driving? See the new calculations” »

They only wanted to watch some k-dramas. 😢

Two teenagers in North Korea have been killed by a firing squad for watching and selling movies from neighbouring South Korea.

Deep Learning AI Specialization: https://imp.i384100.net/GET-STARTED
ChatGPT from Open AI has shocked many users as it is able to complete programming tasks from natural language descriptions, create legal contracts, automate tasks, translate languages, write articles, answer questions, make video games, carry out customer service tasks, and much more — all at the level of human intelligence with 99% percent of its outputs. PAL Robotics has taught its humanoid AI robots to use objects in the environment to avoid falling when losing balance.

AI News Timestamps:
0:00 Why OpenAI’s ChatGPT Has People Panicking.
3:29 New Humanoid AI Robots Technology.
8:20 Coursera Deep Learning AI

Continue reading “Why OpenAI’s New ChatGPT Has People Panicking | New Humanoid AI Robots Technology” »

There are many components that make The Orville: New Horizons a great show, and not the least of which are the beautiful visuals. Please enjoy this compilation of amazing shots from the first six episodes of the third season of The Orville. (Stay tuned for episodes 7–10 in Part 2.)

#RenewTheOrville.

Continue reading “The Amazing Visuals of The Orville: New Horizons (Part 1 of 2)” »

A team of researchers at DeepMind Technologies Ltd., has created an AI application called “DeepNash” that is able to play the game Stratego at an expert level. In their paper published in the journal Science, the group describes the unique approach they took to improve the app’s level of play.

Stratego is a two-player board game and is considered to be difficult to master. The goal for each player is to capture their opponent’s flag, which is hidden among their initial 40 game pieces. Each of the game pieces is marked with a power ranking—higher-ranked players defeat lower-ranked players in face-offs. Making the game more difficult is that neither player can see the markings on the opponent’s game pieces until they meet face-to-face.

Prior research has shown that the complexity of the game is higher than that of chess or go, with 10⁵³⁵ possible game scenarios. This level of complexity makes it extremely challenging for computer experts attempting to create Stratego-playing AI systems. In this new effort, the researchers took a different approach, creating an app capable of beating most human and other AI systems.