Nokia Industry Workshop: Emerging Directions in Visual Coding

Time: Monday, 14 September 2026, 11:00 AM – 12:30 PM

The workshop reviews the latest developments in two-dimensional and volumetric visual content coding, drawing on the collaborative exploration projects of the Joint Video Experts Team (JVET) and Moving Picture Experts Group (MPEG).

After several years of exploration into new video compression technologies, JVET has recently issued the call for proposals (CfP) on future video coding beyond the Versatile Video Coding (VVC) standard. The workshop will begin with a review of the main outcomes of JVET’s exploration work and discuss what to expect from the CfP process and subsequent standardization activities.

AI-based video compression has gained significant momentum in recent years. The workshop will review a broad spectrum of neural-network-based video compression techniques studied in JVET and MPEG, ranging from post-processing filters to implicit neural video representations.

Gaussian splatting has emerged as a promising approach for realistic rendering of volumetric visual content. MPEG has several ongoing and planned projects on standardizing Gaussian splat coding, varying in their timeline, input and output formats, computational complexity, and other key characteristics. The final talk will review these activities and highlight their potential impact on future immersive media applications.

Organizer:
– Dr. Miska M. Hannuksela, Head of Video Research and Standardization, Nokia

Talks

From VVC to the Next Generation of Video Coding: Nokia’s Contributions to Emerging International Standards, Döne Bugdayci Sansli, Principal Researcher, Nokia
The completion of Versatile Video Coding (VVC, H.266) marked a major milestone in video compression, but the demand for improved coding efficiency, reduced complexity, enhanced resilience, and AI-enabled functionality continues to drive innovation. Since the finalization of VVC, the Joint Video Experts Team (JVET) has undertaken extensive exploration activities to identify technologies capable of delivering performance beyond the current state of the art. These efforts have included large-scale exploration experiments, development of the Enhanced Compression Model (ECM), neural-network-based coding studies, and the recent Call for Evidence (CfE) on video compression beyond VVC.

This presentation provides an overview of Nokia’s contributions to this evolution of video coding standardization. We review the technical and procedural steps that followed VVC, discuss the objectives and outcomes of the recent CfE, and describe how Nokia contributed to the advancement and evaluation of candidate technologies. Particular emphasis is placed on Nokia’s role in the development of emerging coding technologies, collaborative software platforms, and the joint response to the CfE that helped establish the technical evidence for launching the next generation of video coding standardization activities. The talk then discusses the recently issued Call for Proposals (CfP) for coding capability beyond VVC and the key research directions shaping the future of compression technology. Finally, the presentation offers a forward-looking perspective on the next three years of standardization. It examines the anticipated evaluation and collaborative phases, the challenges of balancing compression gains with implementation complexity, and the broader industry transition toward increasingly AI-assisted video coding systems. The presentation aims to provide researchers and practitioners with insight into how international video coding standards are developed and how collaborative innovation continues to shape the future of multimedia communications.

AI in Video Coding: From Enhancement to the Future of Compression, Dr. Maria Santamaria, Principal Researcher, Nokia and Dr. Honglei Zhang, Principal Researcher, Nokia
AI is moving from an outside enhancement into the core of compression itself. This talk walks through the toolset driving that shift: neural post-filtering, already deployable on today’s devices and the first AI formally standardized in video coding; in-loop filtering; end-to-end intra coding, paired with proven motion compensation in hybrid designs; video coding for machines, as video increasingly serves AI systems rather than viewers; and implicit neural representations, where video becomes a function rather than a file.

Gaussian Splat Coding: An Overview of Ongoing MPEG Standardization Activities, Dr. Patrice Rondao Alface, Principal Standardization Specialist, Nokia
Gaussian splatting has emerged as a promising representation for immersive visual media, enabling real-time photorealistic rendering with 6DoF navigation. Progress in acquisition and rendering technologies has facilitated deployment on mobile platforms, supporting the creation and consumption of user-generated volumetric content. The growing need to store, transmit, and deliver such content efficiently has motivated the development of dedicated compression technologies that balance coding performance with implementation complexity. In response, MPEG has initiated standardization activities targeting the coding of Gaussian splat representations. This talk presents the rationale, objectives, and current progress of these efforts, and outlines key technical challenges in defining interoperable and efficient coding solutions for Gaussian splat content.

Biographies

Miska M. Hannuksela received his Master of Science degree in engineering and Doctor of Science degree in technology from Tampere University of Technology, Finland, in 1997 and 2010, respectively. He has been with Nokia since 1996 in different roles including research manager/leader positions in the areas of video and image compression, end-to-end multimedia systems, as well as sensor signal processing and context extraction. Currently he works as Bell Labs Fellow and Head of Video Research and Standardization at Nokia Technology Standards, Tampere, Finland.

Dr. Hannuksela has co-authored more than 1600 standardization contributions in JVET, JCT-VC, JVT, MPEG, 3GPP, and DVB. He has been an editor in some editions of H.264/AVC, H.265/HEVC, and H.266/VVC video coding standards, the versatile supplemental enhancement information (VSEI) standard for coded video bitstreams, and several video systems standards, including ISO Base Media File Format, High Efficiency Image File Format (HEIF), file format for NAL unit structured video (ISO/IEC 14496-15), Omnidirectional Media Format (OMAF), and RTP payload formats for H.264/AVC, H.265/HEVC and H.266/VVC. He has been a co-chair in the File Format ad-hoc group of MPEG Systems since 2022. Dr. Hannuksela has co-authored about 40 journal papers and about 180 conference papers.

Döne Bugdayci Sansli is a Principal Researcher at Nokia, Finland, where she conducts research on video compression, image processing, and multimedia systems. Prior to joining Nokia, she worked at Tampere University and Qualcomm. She received the B.Sc. and M.Sc. degrees in Electrical and Electronics Engineering from Middle East Technical University, Turkey. Her research interests include video coding algorithms, signal and image processing, digital imaging, and multimedia standardization activities in MPEG and DVB. She has contributed to the development of advanced coding tools for next generation video compression standards and contributed to scientific publications and patent applications in the field of video coding and multimedia systems.

Maria Santamaria is a Principal Researcher at Nokia specialising in AI-powered video compression. She earned her BSc and MSc degrees in Computer Science from Universidad del Valle (Colombia) and her PhD in Electronic Engineering from Queen Mary University of London (UK). Her research focuses on machine learning methods for video coding, neural network-based compression tools, and next-generation multimedia systems. She is actively involved in international standardisation activities related to video compression and has contributed to scientific publications, patents, and software developments in AI-driven multimedia technologies.

Honglei Zhang is a Principal Researcher in machine learning at Nokia, Finland, where he leads research and standardization activities in AI‑based coding. He received his bachelor’s and master’s degrees in electrical engineering from Harbin Institute of Technology, China, in 1994 and 1996, respectively. With a career spanning both China and Finland, Honglei has held key roles in software engineering and system architecture at Nokia Oy Finland from 1999 to 2013. He later transitioned to academia and earned his Ph.D. in Signal Processing from Tampere University, Finland, in 2019. Honglei has authored over 50 scientific publications and is an inventor of more than 70 patents, with research interests including image and video compression, graph data analysis, and artificial intelligence. He is a recipient of Nokia’s Outstanding Inventor Awards from 2021 to 2024 and currently serves as an Associate Editor of IEEE Transactions on Circuits and Systems for Video Technology (TCSVT). His current research focuses on neural network‑based video coding for both human‑ and machine‑centric applications.

Patrice Rondao Alface (IEEE Senior Member) received the MSc and Ph.D. degrees in Electrical Engineering in 2002 and 2006, respectively, from Université catholique de Louvain (UCLouvain), Belgium. From 2007 to 2009, he was a Multimedia Application Research Engineer at IMEC, Belgium. In 2009, he joined Bell Labs (Alcatel-Lucent, then Nokia) as a Research Scientist where he led several research projects related to immersive media compression and streaming topics. In 2021, Dr. Rondao Alface joined Nokia Technologies as Principal Standardization Specialist and made several contributions to MPEG standards such as ISO/IEC 23090-5 Video-based point cloud coding (V-PCC), ISO/IEC 23090-12 MPEG immersive video (MIV), and ISO/IEC 23090-29 Video-based dynamic mesh coding (V-DMC). He has made key contributions to the first MPEG standard for Gaussian splat coding, i.e., the ISO/IEC 23090-5 V-PCC amendment for Gaussian splat coding. In 2026, Dr. Rondao Alface received the Distinguished Member of Technical Staff (DMTS) recognition. He authored more than 60 peer-reviewed publications, more than 150 inventions and 100 standards input contributions. His research interests include 3D static and dynamic representations, processing, coding, and streaming.