Researchers at the University of Trento, the Institut Polytechnique de Paris, and Snap, Inc. have devised an AI system that uses a framework they call Clustering for Action Decomposition and DiscoverY (CADDY) to learn a set of discrete actions from a large library of video clips that can be used to create new “playable” videos […]
NEWS
Certifiably NVIDIA-powered HPE servers take on AI tasks
Gartner estimates that 37% of all organisations are using AI in anger today and predicts that that number will double to 75% by 2024. To maintain its competitive edge using detailed analysis of every aspect of its operations, one large US supermarket chain alone currently generates 2.5 petabytes of data A DAY! AI processes require […]
Framestore’s Tim Webber ignites his directing career
Framestore’s Chief Creative Officer and Oscar-winning VFX supervisor Tim Webber is making his directorial debut with a short to test the company’s new FUSE (Framestore Unreal Shot engine) VFX pipeline. The project is sci-fi-based and uses existing Framestore IP, but doesn’t appear to represent a shift into full-time filmmaking for either him or the company. […]
NVIDIA’s Cambridge-1 supercomputer is heading to Harlow
The Times has recently reported that, hot on the heels of the announcement of a new Centre of Excellence in Cambridge, NVIDIA has revealed that it is to site its powerful new AI-focused supercomputer at the KAO Data Centre in Harlow, Essex. Cambridge-1, as it is known, which will spend a lot of its time […]
Free Unreal Engine training for furloughed workers and freelancers
Out of adversity and to nobody’s surprise, two of the areas of content creation that have come on in leaps and bounds during the last twelve months are real-time 3D animation and virtual production. These developments have had a big impact on the way VFX artists, animators, graphic artists, film directors and producers work and […]
OpenAI’s DALL-E is “GPT-3 for images”
OpenAI’s latest piece of mind-boggling deep learning wizardry, DALL-E (Dali meets WALL-E, geddit?), is able to create illustrations, photos, renders or any other visual you care to mention just from a description that you provide. For more detail about DALL-E, try this very readable description from Dale Markowitz on The Next Web. GPT-3, for those […]