Codec Avatar Studio: Paired Human Captures for Complete, Driveable, and Generalizable Avatars

To create photorealistic avatars that users can embody, human modeling must be complete (encompass the full body), driveable (able to reproduce motion of the user from lightweight sensors), and generalizable ( i.e., easily adaptable to novel identities). Towards these goals, paired captures, that is, captures of the same subject obtained from systems of diverse quality and availability, are crucial. However, paired captures are rarely available to researchers outside of dedicated industrial labs: Codec Avatar Studio is our proposal to close this gap. Towards generalization and driveability, we introduce a dataset of 256 subjects captured in two modalities: high resolution multi-view scans of their heads, and video from the internal cameras of a headset.