Multimedia research and standardization

Neural networks that are trained too closely on big datasets may struggle to reconstruct compressed video accurately. Content-adaptive neural network tools such as loop-filters can positively exploit this overfitting, improving coding efficiency with negligible decoding costs. Find out how content-adaptation can also enable decoding customization for specific content in addition to these major coding gains.

Discover the leading research by Ruiying Yang, Maria Santamaria, Francesco Cricri, Honglei Zhang, Jani Lainema, Ramin G. Youvalari, Miska M. Hannuksela and Tapio Elomaa.

Image codec performance can be efficiently enhanced through domain adaptation – but its adaptation overhead can compromise its gain. This is where an adaptive multi-scale progressive probability model delivers: effective domain adaptation without the significant overhead. See how this technique could reduce the bitstream size of lossless image codecs by up to 4.8%.

Want to enhance your lossless image compression? Read the whitepaper from Honglei Zhang, Francesco Cricri, Nannan Zou, Hamed R. Tavakoli and Miska M. Hannuksela.

For the last 30 years, image and video compression algorithms have been designed by engineers – but changes may be afoot. With artificial intelligence set to step up the game, model overfitting at inference time may be necessary to improve the efficiency for learning-based codecs. Learn why Nokia is exploring the potential for modified neural networks to streamline the compression process.

Discover more from the article by Honglei Zhang, Francesco Cricri, Hamed R. Tavakoli, Maria Santamaria, Yat-Hong Lam, and Miska M. Hannuksela

For machines intending to perform vision tasks, adapting reconstructed human-ready videos is a must. But how do we address artifacts caused by varying compression rates and unique content? Joint optimization pits content-specific filters against each other for the right to post-process video with fewer resulting artifacts. Discover how this competitive learning can result in greatly improved performances of reconstructed data.

Ready to claim victory over video artifacts? Read the paper by Honglei Zhang, Jukka I. Ahonen, Nam Le, Ruiying Yang, Francesco Cricri.

While video compressing technologies are traditionally tailored to human viewers, growing AI activity is driving up the demand for machine consumption too. NN-VVC combines machine learning and conventional codecs to optimize video compression, transmission and storage for both human and machine consumption. Learn how this ground-breaking research surpassed today’s state-of-the-art codecs to win IEEE ISM 2023’s Best Paper Award.

Discover the award-winning paper by Jukka I. Ahonen, Nam Le, Honglei Zhang, Antti Hallapuro, Francesco Cricri, Hamed Rezazadegan Tavakoli, Miska M. Hannuksela and Esa Rahtu.

E2E learned compression may take the lead in image coding for machines, but its insufficient flexibility in adaptively allocating bits can sacrifice machine vision performance. Leveraging Regions-of-Interest can minimize the bits allocated for backgrounds, resulting in reduced bitrates while retaining the accuracy of machine tasks. Learn more about how this method can achieve impressive gains within learned image codecs.

Ready to find out more? Read the whitepaper by Jukka I. Ahonen, Nam Le, Honglei Zhang, Francesco Cricri and Esa Rahtu.

Convolutional neural networks can unlock extraordinary tools for image and video coding, but their limited precision in floating point arithmetic is inescapably problematic. Our post-training quantization technique stops data corruption in its tracks, dividing operations between integer and floating-point domains for maximum numerical stability. See how this technique can realize uncompromised deep learning performance across a variety of platforms.

Ready for better machine performance? Take a look at the whitepaper by Honglei Zhang, Nam Le, Francesco Cricri, Jukka Ahonen and Hamed Rezazadegan Tavakoli.

Images compressed with neural network-based codecs are often plagued with checkerboard artifacts, degrading picture quality for human, if not machine, eyes. In steps a new codec fine-tuning technique to remove these problematic artifacts, enhancing details for humans and retaining machine performance at no extra cost. Discover how every vision can benefit from this technique.

Set your sights on clearer end-to-end coded images in the whitepaper by Nam Le, Honglei Zhang, Francesco Cricri, Ramin G. Youvalari, Hamed R. Tavakoli, Emre Aksu, Miska M. Hannuksela and Esa Rahtu.

An increasing amount of videos and images are watched by computer algorithms instead of humans. Our research considers how image coding can adapt to non-human eyes, with implications for smart cities, factory robotics, security and much more. Discover how an inference-time content-adaptive approach can improve compression efficiency for machine-consumption without modifying codec parameters.

Want to learn more? Read the article by Nam Le, Honglei Zhang, Francesco Cricri, Ramin Ghaznavi-Youvalari, Hamed R. Tavakoli, Esa Rahtu

Dynamic meshes bring immersive experiences to life, but their full potential can only be unleashed by standards that ensure interoperability. Initially designed for point clouds, the recent MPEG Visual Volumetric Video-based Coding (V3C) framework can extend its talents to efficiently encode and decode these dynamic meshes – on any device. Discover how this approach exceeds the compression performance of today’s best prior art to support tomorrow’s metaverse experiences.

Ready to unlock new immersive opportunities? Get the article by Patrice Rondao Alface, Aleksei Martemianov, Lauri Ilola, Lukasz Kondrad, Christoph Bachhuber and Sebastian Schwarz.
 

Virtual, augmented and mixed reality applications are on the rise, and volumetric video is the fundamental technology enabling the exploration of real-world captured immersive content. Learn how to efficiently store and distribute volumetric video, which is encoded with the family of Visual Volumetric Video-based Coding (V3C) standards.

Curious to know more? Read the article by Lauri Ilola, Lukasz Kondrad, Sebastian Schwarz and Ahmed Hamza

From education to entertainment, capturing the real world in multi-dimensional immersive experiences presents a multitude of opportunities – alongside data-heavy complications. The release of the MPEG standard for video-based point cloud compression (V-PCC) for mobile is an immersive media gamechanger. Discover how V-PCC distribution and storage, and real-time decoding can now be achieved on every single media device on the market. 

Find out more in this article by Sebastian Schwarz and Mika Pesonen

Point clouds are integral to immersive digital representations, enabling quick 3D assessments for navigating autonomous vehicles, robotic sensing and other use cases. This level of innovation requires massive amounts of data – and that’s where Point Cloud Compression (PCC) comes in. See how PCC lightens point cloud transmission for current and next-generation networks.

Discover more in the article by Sebastian Schwarz, Marius Preda, Vittorio Baroncini, Madhukar Budagavi, Pablo Cesar, Philip A. Chou, Robert A. Cohen, Maja Krivokuća, Sébastien Lasserre, Zhu Li, Joan Llach, Khaled Mammou, Rufael Mekuria, Ohji Nakagami, Ernestasia Siahaan, Ali Tabatai, Alexis M. Tourapis, and Vladyslav Zakharchenko.