Google has come up with a new approach to high resolution AI video generation with Lumiere. While most GenAI video models output individual high resolution frames at various points in the sequence (called “distant keyframes”), fill in the missing frames with low-res images to create motion (known as “temporal super-resolution,” or TSR), then up-res that connective tissue (“spatial super-resolution,” or SSR) of non-overlapping frames, Lumiere takes what Google calls a “Space-Time U-Net architecture,” which processes all frames at once, “without a cascade of TSR models, allowing us to learn globally coherent motion.” Continue reading Google Takes New Approach to Create Video with Lumiere AI

Facebook is bringing back FMV (full motion video) games, which use pre-recorded video files to display action. With the work of Facebook AI Research scientists, the new FMV games are much improved, with a system that can extract controllable characters from real-world videos and then control their motion, thus generating new image sequences. Facebook AI Research scientists, in collaboration with Tel Aviv University, also unveiled a system that, unsupervised, converts audio of one singer to the voice of another. Continue reading Facebook Uses AI to Improve Games, Swap Singers’ Voices

Researchers from three international universities working on twisting radio beams for transferring data have achieved transmission speeds of 32 gigabits per second — 30 times faster than current 4G LTE wireless technology. The project, which includes scientists from University of Glasgow and Tel Aviv University, is led by Professor Alan Willner of USC’s Viterbi School of Engineering. Mobile operators should be interested in the technique to supply faster networks and address congestion created by too many users. Continue reading Scientists Send Data 30 Times Faster Than 4G LTE Wireless

During a two-night event hosted by the Academy of Motion Picture Arts and Sciences, neuroscientists and cognitive psychologists met with filmmakers to discuss their impressions of viewer attention and perception. Scientists have studied the mental and physical responses of audiences through eye-tracking experiments and analysis, while filmmakers have relied more on intuition and experience. Both groups are interested in what maintains an individual’s attention during the movie-going experience. Continue reading Cognitive Scientists, Filmmakers Explore Cinematic Perception