SyncAI.news, a Varaisys broadcasting
NBAvatar: Neural Billboards Avatars with Realistic Hand-Face Interaction
DS

David Svitov, Mahtab Dahaghin, Pietro Morerio, Alessio Del Bue

· 1 min read

ResearcharXiv cs.CV

NBAvatar: Neural Billboards Avatars with Realistic Hand-Face Interaction

arXiv:2603.12063v2 Announce Type: replace Abstract: We present NBAvatar - a method for realistic rendering of head avatars handling non-rigid deformations caused by hand-face interaction. To this end, we introduce a novel hybrid implicit-explicit representation for animated avatars by combining the training of explicit oriented planar primitives with implicit neural rendering. Such a combination of representations in the end-to-end pipeline enables NBAvatar to handle temporally and pose-consistent geometry, along with fine-grained appearance details provided by the neural rendering technique. To enable joint optimization of different representations we propose a geometry-aware training scheme that allows our hybrid representation to surpass existing approaches in terms of novel-view and novel-pose rendering quality. Specifically, NBAvatar achieves up to 53% LPIPS reduction compared to Gaussian-based avatar methods, while also improving PSNR and SSIM, and achieves higher structural similarity compared to the state-of-the-art hand-face interaction method InteractAvatar.

Original source

This story was published by arXiv cs.CV and written by David Svitov, Mahtab Dahaghin, Pietro Morerio, Alessio Del Bue. SyncAI.news shows a preview; the complete article is on the publisher's site.

Read the full story on arxiv.org

Similar News