Authentic Hand Avatar from a Phone Scan via Universal Hand Model
This addresses the need for immersive AR/VR experiences by enabling personalized hand avatars from simple scans, though it appears incremental as it builds on existing hand modeling techniques.
The paper tackles the problem of creating authentic 3D hand avatars from phone scans by introducing a universal hand model that simultaneously performs tracking and modeling to avoid accumulated errors, resulting in high-fidelity meshes with a concise pipeline and novel loss function to address skin sliding.
The authentic 3D hand avatar with every identifiable information, such as hand shapes and textures, is necessary for immersive experiences in AR/VR. In this paper, we present a universal hand model (UHM), which 1) can universally represent high-fidelity 3D hand meshes of arbitrary identities (IDs) and 2) can be adapted to each person with a short phone scan for the authentic hand avatar. For effective universal hand modeling, we perform tracking and modeling at the same time, while previous 3D hand models perform them separately. The conventional separate pipeline suffers from the accumulated errors from the tracking stage, which cannot be recovered in the modeling stage. On the other hand, ours does not suffer from the accumulated errors while having a much more concise overall pipeline. We additionally introduce a novel image matching loss function to address a skin sliding during the tracking and modeling, while existing works have not focused on it much. Finally, using learned priors from our UHM, we effectively adapt our UHM to each person's short phone scan for the authentic hand avatar.