SurFhead: Affine Rig Blending for Geometrically Accurate 2D Gaussian Surfel Head Avatars
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917989220089856 |
|---|---|
| author | Lee, Jaeseong Kang, Taewoong Bühler, Marcel C. Kim, Min-Jung Hwang, Sungwon Hyung, Junha Jang, Hyojin Choo, Jaegul |
| author_facet | Lee, Jaeseong Kang, Taewoong Bühler, Marcel C. Kim, Min-Jung Hwang, Sungwon Hyung, Junha Jang, Hyojin Choo, Jaegul |
| contents | Recent advancements in head avatar rendering using Gaussian primitives have achieved significantly high-fidelity results. Although precise head geometry is crucial for applications like mesh reconstruction and relighting, current methods struggle to capture intricate geometric details and render unseen poses due to their reliance on similarity transformations, which cannot handle stretch and shear transforms essential for detailed deformations of geometry. To address this, we propose SurFhead, a novel method that reconstructs riggable head geometry from RGB videos using 2D Gaussian surfels, which offer well-defined geometric properties, such as precise depth from fixed ray intersections and normals derived from their surface orientation, making them advantageous over 3D counterparts. SurFhead ensures high-fidelity rendering of both normals and images, even in extreme poses, by leveraging classical mesh-based deformation transfer and affine transformation interpolation. SurFhead introduces precise geometric deformation and blends surfels through polar decomposition of transformations, including those affecting normals. Our key contribution lies in bridging classical graphics techniques, such as mesh-based deformation, with modern Gaussian primitives, achieving state-of-the-art geometry reconstruction and rendering quality. Unlike previous avatar rendering approaches, SurFhead enables efficient reconstruction driven by Gaussian primitives while preserving high-fidelity geometry. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_11682 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | SurFhead: Affine Rig Blending for Geometrically Accurate 2D Gaussian Surfel Head Avatars Lee, Jaeseong Kang, Taewoong Bühler, Marcel C. Kim, Min-Jung Hwang, Sungwon Hyung, Junha Jang, Hyojin Choo, Jaegul Graphics Artificial Intelligence Computer Vision and Pattern Recognition Recent advancements in head avatar rendering using Gaussian primitives have achieved significantly high-fidelity results. Although precise head geometry is crucial for applications like mesh reconstruction and relighting, current methods struggle to capture intricate geometric details and render unseen poses due to their reliance on similarity transformations, which cannot handle stretch and shear transforms essential for detailed deformations of geometry. To address this, we propose SurFhead, a novel method that reconstructs riggable head geometry from RGB videos using 2D Gaussian surfels, which offer well-defined geometric properties, such as precise depth from fixed ray intersections and normals derived from their surface orientation, making them advantageous over 3D counterparts. SurFhead ensures high-fidelity rendering of both normals and images, even in extreme poses, by leveraging classical mesh-based deformation transfer and affine transformation interpolation. SurFhead introduces precise geometric deformation and blends surfels through polar decomposition of transformations, including those affecting normals. Our key contribution lies in bridging classical graphics techniques, such as mesh-based deformation, with modern Gaussian primitives, achieving state-of-the-art geometry reconstruction and rendering quality. Unlike previous avatar rendering approaches, SurFhead enables efficient reconstruction driven by Gaussian primitives while preserving high-fidelity geometry. |
| title | SurFhead: Affine Rig Blending for Geometrically Accurate 2D Gaussian Surfel Head Avatars |
| topic | Graphics Artificial Intelligence Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2410.11682 |