By
Paula ParisiMay 25, 2022
Google has released a research paper on a new text-to-image generator called Imagen, which combines the power of large transformer language models for text with the capabilities of diffusion models in high-fidelity image generation. “Our key discovery is that generic large language models (e.g. T5), pretrained on text-only corpora, are surprisingly effective at encoding text for image synthesis,” the company said. Simultaneously, Google is introducing DrawBench, a benchmark for text-to-image models it says was used to compare Imagen with other recent technologies including VQGAN+CLIP, latent diffusion models, and OpenAI’s DALL-E 2. Continue reading Google’s Imagen AI Model Makes Advances in Text-to-Image
By
Debra KaufmanFebruary 12, 2019
On February 9, the Academy of Motion Picture Arts and Sciences presented Scientific and Engineering Awards to the teams behind Adobe’s After Effects and Photoshop. David Simons, Daniel Wilk, James Acquavella, Michael Natkin and David M. Cotter accepted the award for After Effects for motion graphics. Thomas Knoll and John Knoll accepted the award for the original architecture, design and development of Photoshop, and Mark Hamburg for its continued development and engineering. Both tools are a mainstay in the film and television industry. Continue reading Photoshop and After Effects Honored with Sci-Tech Awards
By
Debra KaufmanMay 2, 2018
At Facebook’s Oculus, a new project team is developing a VR experience powered by live actors. Oculus executive producer of experiences Yelena Rachitsky, who worked on Pixar’s first VR experience based on the movie “Coco,” describes it as a melding of indie video game “Journey” and immersive play “Sleep No More.” Rachitsky said the company is interested in creating the experience of live actors “without needing to be in a site-specific location.” The experience, tentatively slated for next year, could also create a new revenue stream for the nascent technology. Continue reading Oculus Team Developing VR Experience Featuring Live Actors
By
Rob ScottJanuary 11, 2018
Amazon and Netflix have joined major studios including Disney and Warner Bros. in suing Dragon Box, claiming that the company’s $350 streaming device makes it easy for consumers to access illegal streams of TV shows and movies. The lawsuit alleges that some of the titles, such as Disney’s “Coco,” are still in theaters. Variety reports: “Dragon Box has advertised the product as a means to avoid paying for authorized subscription services, the complaint alleges, quoting marketing material that encourages users to ‘Get rid of your premium channels … [and] Stop paying for Netflix and Hulu.’” Continue reading Studios Take on Dragon Box in Latest Streaming Piracy Battle
By
Debra KaufmanDecember 6, 2017
In May, research project Google Brain debuted its AutoML artificial intelligence system that can generate its own AIs. Now, Google has unveiled an AutoML project to automate the design of machine learning models using so-called reinforcement learning. In this system, AutoML is a controller neural network that develops a “child” AI network for a specific task. The near-term goal is that AutoML would be able to create a child that outperforms human versions. Down the line, AutoML could improve vision for autonomous vehicles and AI robots. Continue reading Google Intends to Advance Machine Learning With its AutoML
By
Debra KaufmanNovember 17, 2017
On November 22, Disney-Pixar will release the animated feature “Coco,” which takes place during Dia de los Muertos, a Mexican holiday honoring the dead. Pixar has also debuted its first VR experience, “Coco VR,” created in partnership with Oculus. “Coco VR” is available on Rift headsets, with a Gear VR version out next week. Pixar dubs the experience a “social adventure” where participants embody skeletal characters and explore the Land of the Dead and the holiday, to learn about the film, the festival and the traditions. Continue reading Pixar Makes Its First Foray into Virtual Reality With ‘Coco VR’
By
Debra KaufmanOctober 17, 2017
Virtual reality has been on a major roll … at least until this year. When Oculus executives sold their startup to Facebook in 2014 for about $3 billion, VR was riding high. The purchase prompted tech giants such as Google and Microsoft to speed up their VR headset development, and sparked a wave of investments and new startups. But this year, interest in VR has arguably slumped, as some consumers seem to have grown disappointed. Oculus has not helped the sentiment, since it has not revealed any official figures about Rift sales, but still very much believes in the technology’s potential. Continue reading Oculus Recognizes Virtual Reality Hype, Defends its Potential