Lightricks has released an AI model called LTX Video (LTXV) it says generates five seconds of 768 x 512 resolution video (121 frames) in just four seconds, outputting in less time than it takes to watch. The model can run on consumer-grade hardware and is open source, positioning Lightricks as a mass market challenger to firms like Adobe, OpenAI, Google and their proprietary systems. “It’s time for an open-sourced video model that the global academic and developer community can build on and help shape the future of AI video,” Lightricks co-founder and CEO Zeev Farbman said. Continue reading Lightricks LTX Video Model Impresses with Speed and Motion

Google is attacking slow-loading web pages with the new JPEG image encoder/decoder Jpegli, which offers a 35 percent compression ratio improvement using high quality compression settings, the Alphabet company says. The Jpegli JPEG coding library offers backward compatibility via “a fully interoperable encoder and decoder complying with the original JPEG standard and its most conventional 8-bit formalism, and API/ABI compatibility with libjpeg-turbo and MozJPEG,” Google says. The resulting images compressed using Jpegli are “more precise and psychovisually effective” as a result of computations that make images “look clearer” with “fewer observable artifacts.” Continue reading Google Introduces Faster, More Efficient JPEG Coding Library

Nikon, the Japanese company best known for still cameras, is vaulting into the mainstream of professional moving images with its acquisition of California-based RED Digital Cinema. RED cameras popular among filmmakers and other creators include the RED ONE 4K and V-RAPTOR [X] series. The company also invented the REDCODE RAW compression technology. On closing, RED will become a wholly-owned subsidiary of Nikon, which plans to merge “Nikon’s expertise in product development” with “RED’s knowledge in cinema cameras, including unique image compression technology and color science.” Continue reading Nikon to Enter Cinema Camera Business with RED Acquisition

Stability AI, purveyor of the popular Stable Diffusion image generator, has introduced a completely new model called Stable Cascade. Now in preview, Stable Cascade uses a different architecture than Stable Diffusion’s SDXL that the UK company’s researchers say is more efficient. Cascade builds on a compression architecture called Würstchen (German for “sausage”) that Stability began sharing in research papers early last year. Würstchen is a three-stage process that includes two-step encoding. It uses fewer parameters, meaning less data to train on, greater speed and reduced costs. Continue reading Stability AI Advances Image Generation with Stable Cascade

AMD is introducing a new encoder chip designed for energy efficient and economical AV1 video streaming. The AV1 codec is increasingly popular as streamers seek to meet massive bandwidth needs. AMD’s new card, the Alveo MA35D, delivers what promises to be a massive leap in throughput and compression over its predecessor. Compression performance is critical in today’s streaming market, where the model has changed from a one-to-many central server model to a cloud-based distributed many-to-many format as entertainment is vying for bandwidth with video conferences, massively multiplayer online games and social media streaming. Continue reading AMD Touts Advance in AV1 Encoding for Streaming Services

Apple has acquired WaveOne, a Mountain View-based startup that has been developing AI algorithms for video compression. Cupertino has been mum about the purchase, but the deal reportedly closed in January, and WaveOne employees are said to have been absorbed into Apple’s machine learning groups. WaveOne’s codecs use machine learning to squeeze more picture out of less bandwidth, including optimizing for signal interruptions, so the picture doesn’t freeze or disappear, making it ideal for mobile. As Netflix and YouTube tout picture improvements, WaveOne could potentially advantage Apple TV+ and a mixed reality headset. Continue reading Apple Eyes AI Video Compression with WaveOne Acquisition

YouTube is experimenting with a higher bitrate 1080p format for Premium subscribers. The enhanced 1080p Premium reportedly provides a better viewing experience. For now, 1080p Premium is only available to a very small group. The existing 1080p HD resolution on YouTube remains unchanged, according to the company. “1080p Premium is an enhanced bitrate version of 1080p which provides more information per pixel that results in a higher quality viewing experience,” explains spokesperson Paul Pennington, clarifying “there are no changes to the existing quality offerings for 1080p (HD) resolution on YouTube.” Continue reading YouTube Testing ‘1080p Premium’ with Its Paid Subscribers

Meta Platforms says its vision for the metaverse will rely heavily on compression technology “to deliver high-quality, uninterrupted experiences for everyone.” With that in mind, it’s trained its Fundamental AI Research (FAIR) lab on developing “hypercompression” solutions. First up is EnCodec, an audio technology it says compresses at 64 kbps, with no loss in quality, and at 10 times the efficiency of MP3. The EnCodec protocol has the potential to  greatly improve the sound and reliability of speech over low-bandwidth (like when your mobile phone is only getting one bar). It also works for music. Continue reading Meta Says Its AI-Compressed Audio Codec Beats MP3 by 10x

On the heels of several successful tests that included Tokyo 2020 Olympics telecasts in Brazil and Japan, Intel is moving full steam ahead to bring live, end-to-end 8K HDR streaming to audiences across the globe. The company sees the future of 8K HDR as revolutionizing the worlds of sports, entertainment and gaming by delivering spectacular, immersive events at stadium scale, augmented by 3D, VR, AR and UHD audio. The key to this brave new broadcast world is Intel’s Xeon Scalable processors for local encoding and delivery over-the-top. And of course, the slickest compression algorithms. Continue reading Intel’s 8K HDR Live Streams ‘Way Beyond Proof of Concept’

University of Ottawa researchers have done some groundbreaking work on lenses, using nanotechnology to develop so-called metalenses that dramatically shrink down optics. But lenses still rely on space to produce images and the researchers have presented the concept of an optical “spaceplate” that propagates light for a distance much longer than the plate thickness, enabling future imaging systems to shrink even further. A spaceplate can be used to miniaturize all kinds of devices that manipulate light. “It’s a possibly revolutionary development in the field of optical science,” suggests photography and camera news site PetaPixel. Continue reading Researchers Use Nanotechnology to Shrink Optics for Devices

At CES 2020, the non-profit standards organization Bluetooth Special Interest Group announced that LE (Low Energy) Audio would be incorporated into its technology, improving a standard signal’s ability to manage and share wireless audio streams between devices — without stressing the batteries. In fact, since 2012, Bluetooth has incorporated LE features, dubbed Bluetooth Smart and BLE, to allow wearables and sensors to stay connected and minimize battery drain. But it has had no impact on wireless audio devices, which LE Audio hopes to remedy. Continue reading CES: Bluetooth SIG’s Low Energy Audio Slows Battery Drain

German research organization Fraunhofer, known for its extensive work in applied sciences, including its contributions to compression tech used for today’s MP3 audio and MP4 video, is now working on 5G virtual reality streaming software. Last year, Fraunhofer revealed its high-speed VR microdisplay hardware. It is now demonstrating new video compression software based on the MPEG-OMAF standard, which allows for streaming of 360-degree video over 5G networks. The goal is to minimize the problems related to resolution, compression artifacts and latency commonly experienced when streaming VR content over 4G and Wi-Fi networks. Continue reading Fraunhofer Compression Tech Used to Stream VR Over 5G

Facebook unveiled Spectrum, an open-source image processing library to help improve the quality and reliability of images uploaded through its own apps. Spectrum, which Facebook first showed publicly and launched in beta in November, is now on GitHub, available to the developer community. As higher quality cameras on smartphones have become a key selling point, consumers are dealing with larger image files, which can be a stumbling block since they eat up more device memory and more network bandwidth. Continue reading Facebook Introduces Open-Source Image Processing Library

JPEG (Joint Photographic Experts Group), known for its photo standard, released a new video compression standard, JPEG XS, designed to work on next-gen 5G cellular or Wi-Fi networks. The new standard, says JPEG, will work on current computers via a software upgrade and is aimed at streaming lossless video, VR content and games over wireless networks, with lower latency and better energy efficiency. Devices smaller than computers, however, will require a hardware upgrade to support JPEG XS. Continue reading JPEG Debuts Streaming Video Format for 5G, Wi-Fi Networks

Waiting for a video to buffer may become an annoyance of the past. Researchers at MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL) are working on streaming algorithms that use AI to improve load rates and, thus, reduce buffering. Dubbed Pensieve, the new technology relies on machine learning to navigate the often-chaotic and ever-changing conditions of networks in real-time, based on a system of rewards (when the video loads smoothly) and penalties (when it’s interrupted). Meanwhile, Netflix is working on its own AI solution to address buffering. Continue reading MIT and Netflix Testing AI-Based Algorithms to Curb Buffering