CloseUpAvatar: High-Fidelity Animatable Full-Body Avatars with Mixture of Multi-Scale Textures
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912746076897280 |
|---|---|
| author | Svitov, David Morerio, Pietro Agapito, Lourdes Del Bue, Alessio |
| author_facet | Svitov, David Morerio, Pietro Agapito, Lourdes Del Bue, Alessio |
| contents | We present a CloseUpAvatar - a novel approach for articulated human avatar representation dealing with more general camera motions, while preserving rendering quality for close-up views. CloseUpAvatar represents an avatar as a set of textured planes with two sets of learnable textures for low and high-frequency detail. The method automatically switches to high-frequency textures only for cameras positioned close to the avatar's surface and gradually reduces their impact as the camera moves farther away. Such parametrization of the avatar enables CloseUpAvatar to adjust rendering quality based on camera distance ensuring realistic rendering across a wider range of camera orientations than previous approaches. We provide experiments using the ActorsHQ dataset with high-resolution input images. CloseUpAvatar demonstrates both qualitative and quantitative improvements over existing methods in rendering from novel wide range camera positions, while maintaining high FPS by limiting the number of required primitives. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_03593 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | CloseUpAvatar: High-Fidelity Animatable Full-Body Avatars with Mixture of Multi-Scale Textures Svitov, David Morerio, Pietro Agapito, Lourdes Del Bue, Alessio Computer Vision and Pattern Recognition We present a CloseUpAvatar - a novel approach for articulated human avatar representation dealing with more general camera motions, while preserving rendering quality for close-up views. CloseUpAvatar represents an avatar as a set of textured planes with two sets of learnable textures for low and high-frequency detail. The method automatically switches to high-frequency textures only for cameras positioned close to the avatar's surface and gradually reduces their impact as the camera moves farther away. Such parametrization of the avatar enables CloseUpAvatar to adjust rendering quality based on camera distance ensuring realistic rendering across a wider range of camera orientations than previous approaches. We provide experiments using the ActorsHQ dataset with high-resolution input images. CloseUpAvatar demonstrates both qualitative and quantitative improvements over existing methods in rendering from novel wide range camera positions, while maintaining high FPS by limiting the number of required primitives. |
| title | CloseUpAvatar: High-Fidelity Animatable Full-Body Avatars with Mixture of Multi-Scale Textures |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2512.03593 |