Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2604.13856 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908966562299904 |
|---|---|
| author | Gao, Yujie Xiao, Yao Zhu, Xiangnan Li, Ya Zhang, Yiyi Zhang, Liqing Zhang, Jianfu |
| author_facet | Gao, Yujie Xiao, Yao Zhu, Xiangnan Li, Ya Zhang, Yiyi Zhang, Liqing Zhang, Jianfu |
| contents | Reconstructing a complete 3D head from a single portrait remains challenging because existing methods still face a sharp quality-speed trade-off: high-fidelity pipelines often rely on multi-stage processing and per-subject optimization, while fast feed-forward models struggle with complete geometry and fine appearance details. To bridge this gap, we propose Any3DAvatar, a fast and high-quality method for single-image 3D Gaussian head avatar generation, whose fastest setting reconstructs a full head in under one second while preserving high-fidelity geometry and texture. First, we build AnyHead, a unified data suite that combines identity diversity, dense multi-view supervision, and realistic accessories, filling the main gaps of existing head data in coverage, full-head geometry, and complex appearance. Second, rather than sampling unstructured noise, we initialize from a Plücker-aware structured 3D Gaussian scaffold and perform one-step conditional denoising, formulating full-head reconstruction into a single forward pass while retaining high fidelity. Third, we introduce auxiliary view-conditioned appearance supervision on the same latent tokens alongside 3D Gaussian reconstruction, improving novel-view texture details at zero extra inference cost. Experiments show that Any3DAvatar outperforms prior single-image full-head reconstruction methods in rendering fidelity while remaining substantially faster. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_13856 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Any3DAvatar: Fast and High-Quality Full-Head 3D Avatar Reconstruction from Single Portrait Image Gao, Yujie Xiao, Yao Zhu, Xiangnan Li, Ya Zhang, Yiyi Zhang, Liqing Zhang, Jianfu Computer Vision and Pattern Recognition Reconstructing a complete 3D head from a single portrait remains challenging because existing methods still face a sharp quality-speed trade-off: high-fidelity pipelines often rely on multi-stage processing and per-subject optimization, while fast feed-forward models struggle with complete geometry and fine appearance details. To bridge this gap, we propose Any3DAvatar, a fast and high-quality method for single-image 3D Gaussian head avatar generation, whose fastest setting reconstructs a full head in under one second while preserving high-fidelity geometry and texture. First, we build AnyHead, a unified data suite that combines identity diversity, dense multi-view supervision, and realistic accessories, filling the main gaps of existing head data in coverage, full-head geometry, and complex appearance. Second, rather than sampling unstructured noise, we initialize from a Plücker-aware structured 3D Gaussian scaffold and perform one-step conditional denoising, formulating full-head reconstruction into a single forward pass while retaining high fidelity. Third, we introduce auxiliary view-conditioned appearance supervision on the same latent tokens alongside 3D Gaussian reconstruction, improving novel-view texture details at zero extra inference cost. Experiments show that Any3DAvatar outperforms prior single-image full-head reconstruction methods in rendering fidelity while remaining substantially faster. |
| title | Any3DAvatar: Fast and High-Quality Full-Head 3D Avatar Reconstruction from Single Portrait Image |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2604.13856 |