OHTA: One-shot Hand Avatar via Data-driven Implicit Priors

Abstract

In this paper, we delve into the creation of one-shot hand avatars, attaining high-fidelity and drivable hand represen-tations swiftly from a single image. With the burgeoning domains of the digital human, the need for quick and per-sonalized hand avatar creation has become increasingly critical. Existing techniques typically require extensive in-put data and may prove cumbersome or even impractical in certain scenarios. To enhance accessibility, we present a novel method OHTA (One-shot Hand avaTAr) that en-ables the creation of detailed hand avatars from merely one image. OHTA tackles the inherent difficulties of this data-limited problem by learning and utilizing data-driven hand priors. Specifically, we design a hand prior model initially employed for 1) learning various hand priors with available data and subsequently for 2) the inversion and fitting of the target identity with prior knowledge. OHTA demonstrates the capability to create high-fidelity hand avatars with con-sistent animatable quality, solely relying on a single image. Furthermore, we illustrate the versatility of OHTA through diverse applications, encompassing text-to-avatar conver-sion, hand editing, and identity latent space manipulation.