Tech Papers 2025: This paper discusses the Avatar Representation Format (ARF), the goal of which is to offer an interoperable exchange format for the storage, carriage, and animation of 3D avatars.
Abstract
Immersive communication and the vision of the “Metaverse” rely on the ability for users to share experiences in 3D virtual and mixed-reality spaces. A crucial aspect of these experiences is the use of avatars – digital representations of users that can convey presence, identity, and expression. Avatars allow people to embody virtual characters or versions of themselves in shared environments, enabling natural interaction and social communication even when physically apart. As augmented reality (AR) and virtual reality (VR) technologies advance, the importance of a standardized avatar format grows. An interoperable avatar format would ensure that users can maintain a consistent digital persona across different applications, platforms, and devices, fostering a seamless 3D communication experience. The Moving Picture Experts Group (MPEG) – within ISO/IEC – has been developing standards for immersive media (MPEG-I), addressing video, audio, and 3D scene representations. Recognizing the need for a common avatar framework, MPEG initiated the Avatar Representation Format (ARF) as part 39 of the MPEG-I ISO/IEC 23090 suite. The goal of ARF is to offer an interoperable exchange format for the storage, carriage, and animation of 3D avatars. In other words, ARF seeks to enable a user’s 3D avatar to be stored, transmitted, and animated in a standard way, so that any conformant system can interpret and render that avatar. By providing a unified format for both the avatar’s visual model and its animations, ARF stands to greatly facilitate immersive communications – from multi-user VR meetings to shared AR experiences – where consistent avatar representation is essential.
Exclusive Content
This article is available with a Technical Paper Pass
Dynamic streaming content packaging with C2PA
Tech Papers 2026: This paper presents an implementation of the approach adopted by C2PA for live video to dynamic packaging.
Dynamic power control for sustainable broadcast transmitter networks
Tech Papers 2026: This paper proposes an approach that uses predictive modelling in combination with real-time interference monitoring to optimise transmitter powers dynamically, with minimal impact on the consumer.
A standardised framework for C2PA provenance in media workflows
Tech Papers 2026: This paper presents the first standardised framework for implementing C2PA for media provenance across newsrooms of varying sizes and operational contexts.
Building MXL together: Progress of the multi-vendor open-source media exchange SDK
Tech Papers 2026: This paper presents the Media eXchange Layer (MXL), an open-source SDK project hosted by the Linux Foundation in collaboration with the EBU and NABA.
Search first, inspect visually when needed: A multi-agent architecture for semantic video archival retrieval
Tech Papers 2026: This paper introduces Smart Chat, a multi-agent video question-answering system that searches indexed video moments, localizes candidate evidence, and inspects a short clip only when visual verification is needed.