Artificial Intelligence


NVIDIA AI Omniverse Audio2Face Human Face
Let’s face it, voice actors are typically easier to find and won’t cost you as much, but sometimes, the audio track may need a face. Meet NVIDIA’s Omniverse Audio2Face. Put simply, it can generate an animation of a 3D character to match any voice-over track, whether it be for a video game, movie, real-time digital assistants, or just as an experiment. You can make use of the app for interactive real-time applications or as a traditional facial animation authoring tool. Read more for a video demonstration and additional information.

NVIDIA Canvas Update AI Demo App
The free NVIDIA Canvas beta app has been updated, and it offers an incredible real-time painting tool GauGAN to anyone with an NVIDIA RTX GPU. Put simply, artists can utilize advanced AI to quickly turn simple brushstrokes into photorealistic landscape images or just as a tool to speed up concept exploration, thus freeing more time to visualize ideas. This update is powered by the GauGAN2 AI model and NVIDIA RTX GPU Tensor Cores, resulting in increased quality as well as 4x higher resolution. Read more for a video demonstration and additional information.

Beyond Imagination Beomni Humanoid Robot AI Brain CES
Beyond Imagination’s Beomni is touted as one of the world’s most advanced general-purpose humanoid robots, thanks to an evolving “AI Brain” that enables it to assist its human pilot in performing a multitude number of tasks. One example would be performing scientific experiments in challenging environments like microgravity. This means its human pilot can remain safely on the ground, while leveraging Beomni’s low-latency remote video feed and natural controls. Read more for two videos, including an in-depth look from CES 2022, and additional information.

Huawei Engineer China Self-Driving Driverless Bicycle
Huawei AI engineer Zhihui Jun has always been intrigued by autonomy, whether it be smart cars or military vehicles. So, he decided to put his passion to work by developing a self-driving bicycle. This electric bicycle, powered by a lithium-ion battery good for 2-3 hours on a single charge, comes equipped with various sensors like LiDAR, accelerometers, and gyroscopes, to help it navigate obstacles as well as stand on its own. Read more for a video and additional information.

Morgan Freeman Deepfake
Bob de Jong knew that a computer-generated Morgan Freeman would not be complete without a competent voice actor, and this amazing AI-generated model was the result. It may look like Morgan Freeman, but the real star is voice actor Boet Schouwink who could make you think the actor is actually speaking. This particular deepfake was most likely created with the help of a generative adversarial network (GAN). Read more for two videos, including a behind-the-scenes.

AI Upscale Colorize Downtown Los Angeles 1930
Downtown Los Angeles in the 1930s was definitely something else, and thanks to the power of AI, we’re able to get a somewhat clear look at rare footage uncovered by A/V Geeks. On the technical side, the FPS was boosted to 60 frames per second, image resolution given an HD makeover, and then colorized only for the ambiance. Read more for the remastered version as well as the original footage.

Engineered Arts Ameca Humanoid Robot AI Platform
Set to make its public debut at CES 2022 next month in Las Vegas, Engineered Arts’ Ameca humanoid robot AI platform is claimed to be the world’s most advanced human shaped robot representing the forefront of human-robotics technology. Remember David and Walter from the movie “Prometheus”? Ameca is set to be a platform for development into future robotics technologies, and could pave the way for a similar robot if given the ability to learn on its own. Read more for a video and additional information.

Xenobots Self-Replication Robot Biology
Researchers from the University of Vermont, Tufts University, and the Wyss Institute for Biologically Inspired Engineering at Harvard University have created the first-ever, self-replicating living robots, called Xenobots 3.0. What is a living robot? They are capable of going out, finding cells, and build copies of themselves repeatedly. They are made from 3,000 embryonic skin cells of an African clawed frog. Read more for a video and additional information.

Artificial Intelligence Robot Artist Ai-Da Pyramids Giza
Ai-Da, named after mathematician Ada Lovelace, made an appearance at the Giza Pyramid Complex, but it wasn’t smooth sailing. She was actually seized by border agents upon her arrival, as authorities feared the robot may have been hiding covert spy tools. Ai-Dai presented her sculpture, titled “Immortal Riddle,” a play on the ancient Egyptian considerations of the afterlife and our current obsession with using biotechnology to achieve immortality in the 21st century. Read more for two videos and additional information.

ETH Zurich Research Robot Artificial Intelligence Hanging Gardens
ETH Zurch researchers have partnered with Müller Illien Landscape Architects, Timbatec and other partners to construct hanging gardens that stand 74-feet-tall. It consists of five geometrically complex wooden pods that are slightly offset from each other and supported by eight thin steel pillars. This installation, named after the Babylonian queen, is being designed and built using innovative digital methods, including robots as well as artificial intelligence. Read more for a video and additional information.