Bringing Your Portrait to 3D Presence
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866913003312513024 |
|---|---|
| author | Zhang, Jiawei Chu, Lei Li, Jiahao Zang, Zhenyu Li, Chong Li, Xiao Cao, Xun Zhu, Hao Lu, Yan |
| author_facet | Zhang, Jiawei Chu, Lei Li, Jiahao Zang, Zhenyu Li, Chong Li, Xiao Cao, Xun Zhu, Hao Lu, Yan |
| contents | We present a unified framework for reconstructing animatable 3D human avatars from a single portrait across head, half-body, and full-body inputs. Our method tackles three bottlenecks: pose- and framing-sensitive feature representations, limited scalable data, and unreliable proxy-mesh estimation. We introduce a Dual-UV representation that maps image features to a canonical UV space via Core-UV and Shell-UV branches, eliminating pose- and framing-induced token shifts. We also build a factorized synthetic data manifold combining 2D generative diversity with geometry-consistent 3D renderings, supported by a training scheme that improves realism and identity consistency. A robust proxy-mesh tracker maintains stability under partial visibility. Together, these components enable strong in-the-wild generalization. Trained only on half-body synthetic data, our model achieves state-of-the-art head and upper-body reconstruction and competitive full-body results. Extensive experiments and analyses further validate the effectiveness of our approach. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_22553 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Bringing Your Portrait to 3D Presence Zhang, Jiawei Chu, Lei Li, Jiahao Zang, Zhenyu Li, Chong Li, Xiao Cao, Xun Zhu, Hao Lu, Yan Computer Vision and Pattern Recognition We present a unified framework for reconstructing animatable 3D human avatars from a single portrait across head, half-body, and full-body inputs. Our method tackles three bottlenecks: pose- and framing-sensitive feature representations, limited scalable data, and unreliable proxy-mesh estimation. We introduce a Dual-UV representation that maps image features to a canonical UV space via Core-UV and Shell-UV branches, eliminating pose- and framing-induced token shifts. We also build a factorized synthetic data manifold combining 2D generative diversity with geometry-consistent 3D renderings, supported by a training scheme that improves realism and identity consistency. A robust proxy-mesh tracker maintains stability under partial visibility. Together, these components enable strong in-the-wild generalization. Trained only on half-body synthetic data, our model achieves state-of-the-art head and upper-body reconstruction and competitive full-body results. Extensive experiments and analyses further validate the effectiveness of our approach. |
| title | Bringing Your Portrait to 3D Presence |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2511.22553 |