NBAvatar: Neural Billboards Avatars with Realistic Hand-Face Interaction
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917335569268736 |
|---|---|
| author | Svitov, David Dahaghin, Mahtab |
| author_facet | Svitov, David Dahaghin, Mahtab |
| contents | We present NBAvatar - a method for realistic rendering of head avatars handling non-rigid deformations caused by hand-face interaction. We introduce a novel representation for animated avatars by combining the training of oriented planar primitives with neural rendering. Such a combination of explicit and implicit representations enables NBAvatar to handle temporally and pose-consistent geometry, along with fine-grained appearance details provided by the neural rendering technique. In our experiments, we demonstrate that NBAvatar implicitly learns color transformations caused by face-hand interactions and surpasses existing approaches in terms of novel-view and novel-pose rendering quality. Specifically, NBAvatar achieves up to 30% LPIPS reduction under high-resolution megapixel rendering 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_12063 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | NBAvatar: Neural Billboards Avatars with Realistic Hand-Face Interaction Svitov, David Dahaghin, Mahtab Computer Vision and Pattern Recognition We present NBAvatar - a method for realistic rendering of head avatars handling non-rigid deformations caused by hand-face interaction. We introduce a novel representation for animated avatars by combining the training of oriented planar primitives with neural rendering. Such a combination of explicit and implicit representations enables NBAvatar to handle temporally and pose-consistent geometry, along with fine-grained appearance details provided by the neural rendering technique. In our experiments, we demonstrate that NBAvatar implicitly learns color transformations caused by face-hand interactions and surpasses existing approaches in terms of novel-view and novel-pose rendering quality. Specifically, NBAvatar achieves up to 30% LPIPS reduction under high-resolution megapixel rendering 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. |
| title | NBAvatar: Neural Billboards Avatars with Realistic Hand-Face Interaction |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2603.12063 |