AI-based Image-As-Video Streaming

基于人工智能的图像视频流

• 批准号: 59404
• 金额: $ 6.37万
• 依托单位: DEEP RENDER LTD
• 依托单位国家: 英国
• 项目类别: Feasibility Studies
• 财政年份: 2020
• 资助国家: 英国
• 起止时间: 2020 至 无数据
• 项目状态: 已结题
• 来源: https://gtr.ukri.org/projects?ref=59404
• 关键词: AI; based; Image; Video; Streaming

Deep Render Ltd is a London based deep-tech start-up developing the next generation of AI-based media compression algorithms. Our proprietary and patented technology is at the forefront of machine learning research.Deep Render is combining the fields of artificial intelligence, statistics and information theory to unlock the fundamental limits of image and video compression: The human eye is the best data compressor known to humanity - with compression ratios at least 2,000 times better than everything developed to date. Our Biological Compression approach approximates the neurological processes of the human eye through a non-linear, learning-based approach, thereby creating a novel class of highly efficient compression algorithms. We are world leaders in this domain, and our unique, AI-based image compression technology is already providing a 75% efficiency gain over the best previous compression standards.As global data consumption is growing exponentially with more than 80% of traffic being Image/Video, Deep Render's AI-based compression technology is vital to bypass broadband constraints. The outbreak of COVID-19 has now accelerated this growth, as a result of the crisis, internet usage has increased significantly. In particular, the demand for live-streaming and video-chat services. Therefore we want to apply our already working image compression codec to live-video streaming.The outcome of the project is to extend our image compression codec to an image-as-video live-streaming codec, at least 75% more efficient than the current state-of-the-art. Our target customers are the live video chat services (Zoom, Skype, Microsoft Teams), as well as the entertainment industry, including live streaming platforms (Twitch, Facebook, Instagram, YouTube).Our value proposition is easy to understand. By making file sizes 75% smaller, we directly increase the bandwidth supply of the internet for live-streaming by a factor of 4\. Increasing the bandwidth supply by making file sizes smaller, is magnitudes more value- and time-efficient than increasing the bandwidth supply through rewiring the globe with progressively more fibre-cables. Deep Render is going to help create a new age in which bandwidth constraints are a problem of the past. As a result of COVID 19 solving this problem has gained more importance and Deep Render is determined to create a fast solution.

Deep Render Ltd是一家总部位于伦敦的深度技术初创公司，开发基于人工智能的下一代媒体压缩算法。我们的专有和专利技术处于机器学习研究的前沿。深度渲染结合了人工智能、统计学和信息论的领域，解锁了图像和视频压缩的基本限制：人眼是人类已知的最好的数据压缩器-压缩比至少是迄今开发的任何东西的2000倍。我们的生物压缩方法通过一种非线性的、基于学习的方法来近似人眼的神经过程，从而创建了一类新的高效压缩算法。我们是该领域的世界领先者，我们独特的基于AI的图像压缩技术已经提供了比以前最好的压缩标准提高75%的效率。随着全球数据消耗呈指数级增长，超过80%的流量是图像/视频，Deep Render的基于AI的压缩技术对于绕过宽带限制至关重要。新冠肺炎的爆发现在加速了这种增长，由于这场危机，互联网使用量大幅增加。尤其是对直播和视频聊天服务的需求。因此，我们希望将我们已经在工作的图像压缩编解码器应用到实时视频流中。该项目的结果是将我们的图像压缩编解码器扩展到图像即视频直播编解码器，比目前最先进的编解码器的效率至少提高75%。我们的目标客户是实时视频聊天服务(Zoom、Skype、Microsoft Teams)以及娱乐行业，包括直播流媒体平台(Twitch、Facebook、Instagram、YouTube)。我们的价值主张很容易理解。通过将文件大小缩小75%，我们将互联网直播的带宽供应直接增加了4倍。通过缩小文件大小来增加带宽供应，比通过逐步使用更多的光缆重新布线来增加带宽供应更具价值和时间效益。深度渲染将帮助创造一个新时代，在这个时代，带宽限制已经成为过去的问题。作为COVID 19的结果，解决这个问题变得更加重要，并且Deep Render决心创建一个快速的解决方案。