← ArchivePaper2020
The Rocketbox Library and the Utility of Freely Available Rigged Avatars
Mar Gonzalez-Franco, Eyal Ofek, Ye Pan, Angus Antley, Anthony Steed, Bernhard Spanlang, Antonella Maselli, Domna Banakou, Nuria Pelechano, Sergio Orts-Escolano, Veronica Orvalho, Laura Trutoiu, Markus Wojcik, Maria V. Sanchez-Vives, Jeremy N. Bailenson, Mel Slater, Jaron Lanier
Opens the Microsoft Rocketbox library of rigged avatars for research and academic use, and makes the case for freely available rigged characters as shared infrastructure.
Abstract
As part of the open sourcing of the Microsoft Rocketbox avatar library for research and academic purposes, here we discuss the importance of rigged avatars for the Virtual and Augmented Reality (VR, AR) research community. Avatars, virtual representations of humans, are widely used in VR applications. Furthermore many research areas ranging from crowd simulation to neuroscience, psychology or sociology have used avatars to investigate new theories or to demonstrate how they influence human performance and interactions. We divide this paper in two main parts: the first one gives an overview of the different methods available to create and animate avatars. We cover the current main alternatives for face and body animation as well introduce upcoming capture methods. The second part presents the scientific evidence of the utility of using rigged avatars for embodiment but also for applications such as crowd simulation and entertainment. All in all this paper attempts to convey why rigged avatars will be key to the future of VR and its wide adoption.
How to read this
- Category
- Resource paper announcing the open sourcing of an avatar library, with a survey of what such libraries are for.
- Contributions
- The release of the Microsoft Rocketbox avatar library for research and academic use, previously a commercial product.
- A set of rigged, animation-ready human avatars covering a range of ages, ethnicities and occupations.
- A discussion of why freely available rigged avatars matter as shared infrastructure for virtual reality and embodiment research.
- A survey of the uses the authors expect, drawn from a notably broad list of co-authors across the field.
- Context
- Stands apart from the rest of this cluster: it is infrastructure rather than method, and it has no technical ancestor in the archive. Orvalho is one of the seventeen co-authors, which is how it arrived here. Its practical relevance to rigging is that it is one of the few sources of consistently rigged, redistributable human characters, which is exactly what method papers keep needing and cannot usually cite.
- Correctness
- There is no algorithm to be right or wrong about. The claims to weigh are about utility and coverage, and the honest limits are the ones any fixed asset library has: the rigs reflect one vendor's conventions, the body and face topology is fixed, and the demographic coverage is broad but finite. Its 190 or so citations are the real evidence that the release mattered.
- Clarity
- Written as a resource announcement, easy to read, light on formalism. The asset tables are the substance.
- How to read it
- First pass: abstract and the figures showing the avatar range, then go straight to the GitHub repository, which is the actual deliverable. Second pass: the use cases section if you are choosing between avatar libraries. There is no third pass here, this is a paper you cite and a repository you download.
Related work
- A Deep Dive into Universal Scene Description and Hydra 2019 / SIGGRAPH Courses
- Building Scalable and Evolutive USD Pipelines on Distributed Architecture at Ubisoft 2022 / DigiPro
- Conduit: A Modern Pipeline for the Open Source World 2019 / SIGGRAPH
- Physics-Based Motion Retargeting from Sparse Inputs 2023 / SCA
Keywords
This page summarises the entry and links to its original source. The archive never hosts or redistributes the publication itself.Show it in the full archive list →