Exhibitor profile for iSIZE

You are here

About us

iSize is deep-tech company headquartered in London that specialises in deep learning for efficient, intelligent and sustainable video delivery. iSize patented technology is powered by the latest AI innovations to enable clients to reach more users, provide better experiences and reduce the financial and environmental costs associated with video delivery. iSize products provide innovations spanning encoding, denoising and generative video content creation.


Over the last three decades, advances in video coding algorithms have led to ever improving compression rates. With video occupying more than 80% of all IP traffic by 2022, the end of the quest for bitrate saving is not in sight: every network upgrade is quickly diminished by the increasing demand for content. A multitude of different video coding standards are available to tackle this issue, with every codec generation aiming at 30-50% increase in compression efficiency at the expense of increasing complexity. The latter aspect means that new standards are being adopted very slowly: for instance, while MPEG HEVC was standardized in 2013, its high licensing fees and complexity (especially for HD and 4K content) have not yet allowed for wide adoption. Where does iSIZE fit in? iSIZE is the first company to offer proprietary machine learning solutions for substantial bitrate or quality gains in video compression. Beyond its performance, what makes our solution stand out is that it is compatible with any existing video coding infrastructure. Therefore, it can: boost the compression efficiency of any video codec; run on client devices with minimal or no additional overhead; offer significant computational and energy efficiency for video encoding on resource-constrained devices (drones, action-cams, smartphones, etc.). These advantages allow our clients to seamlessly integrate our solution and benefit from bitrate saving and quality improvement for their video delivery services. Our Core Innovation Future coding standards, like the ongoing VCEG/MPEG JVET and the AOMedia AV2 standardizations will create the next generation codecs that will replace HEVC and VP9/AV1. Such efforts undertake a lengthy development process that will typically culminate in 30%-40% bitrate saving for the same visual quality. However, the expected timeline for delivery of the first working codecs for MPEG’s JVET and AOMedia’s AV2 standardizations are scheduled for after 2023 – at the same time, the HEVC standard (finalized in 2013) has still not reached large rollout to date. On the other hand, current machine learning solutions like Magic Pony (Twitter) and Wave One offer disruptive performance for still-image coding; however, such solutions face substantial barriers when moved to video due to the unresolved challenge of incorporating temporal prediction and their deployment complexity. Our bitrate saving and quality improvements are achieved by incorporating iSize’s proprietary deep perceptual optimisation and precoding technologies as a preprocessing stage of a standard codec pipeline. The entire process is shown in Figure 1. Instead of abandoning the existing codec pipeline (as proposed by deep autoencoding solutions, such as Magic Pony/Twitter and Wave One), iSIZE’s encoder-side solution preprocesses the input content with a custom-designed deep neural network solution. No changes are required in the encoding, stream packaging, streaming and decoding sides to obtain the final result. Our IP offers up to 40% bitrate saving over a wide range of encoding standards and encoding recipes, or commensurate quality improvement (e.g., 6 to 10 point increase in VMAF or similar high-level perceptual quality metrics). These gains can be used to also reduce encoding complexity, thereby saving datacenter processing power and energy consumption. Unlike other machine learning efforts in this space, our solution is deployable today, and can be used on top of any standards-compliant or proprietary video codec architecture with minimal increase in complexity.
iSIZE BitSave: High-quality video at lower bitrates via Intel DL Boost
This white paper describes iSIZE’s innovative BitSave technology, an AI-based perceptual optimization that adaptively filters
Deep perceptual optimization for video encoding
This blog is based on a presentation made by Dr Yiannis Andreopoulos of iSIZE, as part of the Stanford Compression Workshop.
iSIZE releases BitClear to make unwatchable videos watchable by eliminating compression artifacts in user-generated content
iSIZE has developed BitClear, an AI-based video processing technology that removes compression artifacts (like blurring and blocking artifacts) from user-generated (or heavily-compressed) content.
iSIZE joins with BBC R&D and Queen Mary University of London to improve video streaming with new disruptive technology
SEQUOIA, an R&D project partnership between iSIZE, the BBC R&D and Queen Mary University of London (QMUL), has been awarded £700k from Innovate UK following a competitive grant submission, and a rigorous review and award process (<5% acceptance rate). Innovate UK is part of UKRI, the national funding agency investing in science and industrial research in the UK. SEQUOIA looks at the way new technology, including artificial intelligence, can discontinuously change the way we distribute video content. It is a response to the pressing need for video streaming to become more sustainable. It addresses the challenges faced by the media sector in tackling the surge in online media consumption, which is posing unprecedented stress on network infrastructures worldwide. As well as imposing content delivery bottlenecks, this massive load on the internet infrastructure affects how content can be distributed efficiently to larger numbers of viewers, and contributes to its environmental footprint. The project recognises that innovation in video streaming is urgently required. It is looking at perceptual optimization of video streams as a way of making significant reductions in bandwidth required for equal quality. This is at the heart of iSIZE’s work, and the company has built extensive IP and expertise in this domain. This will be combined with innovations in encoding technologies and optimization, which is pursued by BBC R&D and QMUL. “The problems facing video streaming are real and represent significant environmental issues,” said Sergio Grce, CEO of iSIZE. “The increase in video encoding complexity is outpacing Moore’s Law’, and some respected researchers suggest that the carbon footprint of the internet is greater than that of aviation. So this is an issue that must be addressed.’’ “We are very excited to be working with the BBC and QMUL on this project,” he added. “SEQUOIA brings us together with BBC and QMUL to advance the video streaming, incorporating our expertise in deep perceptual optimization and the latest cutting-edge AI innovation. This project will deliver significant financial and environmental improvements for video streaming.” Disruptive innovation for video streaming is urgently needed: new pre and post processing, encoding and delivery tools that are device-aware and cross-codec compatible. This is vital to meet the growing demand for online video, reducing processing, energy and storage requirements. This project will make an impact at every stage in the media distribution chain, demonstrating its results on operational and portable encoder designs, applicable both to video on demand and live streams. This will lead to benefits for the whole sector, demonstrating technology to enable sustainable distribution of Ultra High Definition content, while limiting the impact of video on internet traffic and reducing distribution costs. Extending beyond the commercial benefits, project outcomes will be devised to support environmentally conscious solutions by monitoring and proactively reducing energy consumption at all stages within the media value chain. The partnership of iSIZE, BBC and QMUL brings unique expert know-how and expertise on AI, video coding standardisation, adaptive video pre/post processing and streaming, perceptual optimizations and interoperable software architectures to collaboratively work towards these challenging objectives.
iSIZE presents a paper at CVPR, the world-leading computer vision and AI conference
iSIZE is to present some elements of its ground-breaking technology at CVPR. CVPR is the premier computer vision conference and artificial intelligence worldwide, and features presentations from leading figures in industry and academia. It is organised by CVF, the Computer Society, a part of IEEE, and acceptance/rejection decisions are based on very rigorous peer review by leading experts. The 2021 event will take place virtually, from 19 to 25 June. iSIZE applies artificial intelligence to video systems, modelling the way the eye perceives visual information. This can be used in a number of applications, the primary of which is video streaming. Within video streaming systems, iSIZE preprocesses the input video stream prior to passing it on to a conventional encoder. The final output can be received and decoded by any device, but at a significantly reduced bitrate for any given quality level. This is all achieved with as low as 3ms latency, without requiring any changes to the existing streaming pipeline, and can also be used for energy and cost savings in video and game streaming systems. The CVPR paper outlines some of the concepts used by iSIZE for rate-aware deep perceptual preprocessing and also presents extensive test results and comparisons against the state-of-the-art under very stringent test conditions. “We are excited to present our work at CVPR. Our deep perceptual preprocessing is the first-of-a-kind neural processing component applied for bitrate reduction over state-of-the-art video coding. Similar to the psychoacoustic preprocessing in mp3 audio (and beyond) that delivered music over the web with significantly improved efficiency, we see our approach as a key step towards AI-based psychovisual preprocessing for optimized video processing and delivery.” said Andreopoulos, the CTO of iSIZE, and Professor at University College London in the UK. “Given that this is an entirely new approach for increased efficiency across the video encoding and streaming landscape, sharing some elements of our work via top-tier peer review at conferences like CVPR is important,” he added. “Unlike other proposals in recent years, this research is applicable today with existing and upcoming state-of-the-art coding standards, from AVC all the way to AV1, AV2 and VVC, which form the backbone of all current and future video streaming services.” More information on CVPR can be found at cvpr2021.thecvf.com.
iSIZE raises $6.3m in funding led by Octopus Ventures to tackle environmental impact of video streaming
Investment will enable iSIZE to accelerate its traction and to continue strengthening its technical team and patent portfolio iSIZE has already secured licensing agreements with leading technology and streaming companies iSIZE today announces that it has raised a further $6.3 million in funding as it seeks to make streaming more environmentally friendly without reducing quality. The round was led by Octopus Ventures, with participation from existing investors including TD Veen and Patrick Pichette, Chairman of Twitter and ex-CFO of Google. This brings the total funding raised by the company to $8.2 million. The amount of video streamed over the internet is at all-time high, a trend which has been accelerated by the pandemic and the shift to working from home. At the same time, streaming and content companies are facing pressure from users and advertizers to deliver ever-increasing video quality. With forecasts projecting video to reach 82% of total global internet traffic by 2022, there is also growing awareness of its carbon footprint, with research indicating that it already contributes to more than 1% of global emissions. As a result, streaming and content providers are increasingly turning to technology to address the challenge of delivering a reliable and high-quality experience while managing the financial and environmental costs of doing so. To help solve this problem, iSIZE has pioneered deep-learning solutions that optimize video streaming quality while reducing bitrate requirements, allowing for a significant reduction in data and energy consumption. The potential impact of its technology is huge and iSIZE has already attracted attention from some of the world’s largest technology companies to whom they already licensed their BitSave technology. Headquartered in London, iSIZE was founded by Sergio Grce and Dr. Yiannis Andreopoulos who saw an opportunity to tackle the challenges caused by the explosion of video streaming. The founding team combines many years of research in machine learning, neural networks and video signal processing, evidenced by dozens of research publications. The company is also a graduate of the Creative Destruction Lab Oxford 2019-2020 programme where it received advice and investment from expert mentors. iSIZE intends to use the funding raised to accelerate its traction in the U.S and to further strengthen its technical team and patent portfolio to continue improving the results and innovations it delivers to its customers. Sergio Grce, Founder and CEO of iSIZE, commented: “Today there are more people streaming more video than ever before. Our customers recognize both the commercial opportunity and their social responsibility to optimize their video delivery pipelines with our pioneering technology. We are excited to partner with Octopus Ventures to tap into their network and expertize in building world-changing companies.” Simon King, Partner and deep tech investor at Octopus Ventures, said: “The technology iSIZE has created is pioneering and is already being used by some of the world’s largest companies to reduce the costs and energy used in streaming. Consumer demand for high quality video is only going to increase as our devices are upgraded, so it’s vital that we find new ways to reduce the environmental impact. We are very familiar with this space having been an investor in Magic Pony and Sergio is one of those visionary founders who we believe can build something truly special.” iSIZE’s leading product is a proprietary AI-trained, deep perceptual optimizer that is trained to ‘see with the human eye’ in order to optimize video quality and deliver significant bitrate savings. Its technology has applications across VoD, live streaming, gaming and IoT and bolts-on to the existing conventional video delivery pipeline while integrating with all video encoding standards (including AVC, HEVC and AV1) – all without requiring changes to the streaming process or to end-users’ devices. This allows its customers to improve the end-user experience and reduce costs without breaking standards and with minimal deployment risk.