HairCUP: Hair Compositional Universal Prior for 3D Gaussian Avatars
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866916864115867648 |
|---|---|
| author | Kim, Byungjun Saito, Shunsuke Nam, Giljoo Simon, Tomas Saragih, Jason Joo, Hanbyul Li, Junxuan |
| author_facet | Kim, Byungjun Saito, Shunsuke Nam, Giljoo Simon, Tomas Saragih, Jason Joo, Hanbyul Li, Junxuan |
| contents | We present a universal prior model for 3D head avatars with explicit hair compositionality. Existing approaches to build generalizable priors for 3D head avatars often adopt a holistic modeling approach, treating the face and hair as an inseparable entity. This overlooks the inherent compositionality of the human head, making it difficult for the model to naturally disentangle face and hair representations, especially when the dataset is limited. Furthermore, such holistic models struggle to support applications like 3D face and hairstyle swapping in a flexible and controllable manner. To address these challenges, we introduce a prior model that explicitly accounts for the compositionality of face and hair, learning their latent spaces separately. A key enabler of this approach is our synthetic hairless data creation pipeline, which removes hair from studio-captured datasets using estimated hairless geometry and texture derived from a diffusion prior. By leveraging a paired dataset of hair and hairless captures, we train disentangled prior models for face and hair, incorporating compositionality as an inductive bias to facilitate effective separation. Our model's inherent compositionality enables seamless transfer of face and hair components between avatars while preserving identity. Additionally, we demonstrate that our model can be fine-tuned in a few-shot manner using monocular captures to create high-fidelity, hair-compositional 3D head avatars for unseen subjects. These capabilities highlight the practical applicability of our approach in real-world scenarios, paving the way for flexible and expressive 3D avatar generation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_19481 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | HairCUP: Hair Compositional Universal Prior for 3D Gaussian Avatars Kim, Byungjun Saito, Shunsuke Nam, Giljoo Simon, Tomas Saragih, Jason Joo, Hanbyul Li, Junxuan Computer Vision and Pattern Recognition We present a universal prior model for 3D head avatars with explicit hair compositionality. Existing approaches to build generalizable priors for 3D head avatars often adopt a holistic modeling approach, treating the face and hair as an inseparable entity. This overlooks the inherent compositionality of the human head, making it difficult for the model to naturally disentangle face and hair representations, especially when the dataset is limited. Furthermore, such holistic models struggle to support applications like 3D face and hairstyle swapping in a flexible and controllable manner. To address these challenges, we introduce a prior model that explicitly accounts for the compositionality of face and hair, learning their latent spaces separately. A key enabler of this approach is our synthetic hairless data creation pipeline, which removes hair from studio-captured datasets using estimated hairless geometry and texture derived from a diffusion prior. By leveraging a paired dataset of hair and hairless captures, we train disentangled prior models for face and hair, incorporating compositionality as an inductive bias to facilitate effective separation. Our model's inherent compositionality enables seamless transfer of face and hair components between avatars while preserving identity. Additionally, we demonstrate that our model can be fine-tuned in a few-shot manner using monocular captures to create high-fidelity, hair-compositional 3D head avatars for unseen subjects. These capabilities highlight the practical applicability of our approach in real-world scenarios, paving the way for flexible and expressive 3D avatar generation. |
| title | HairCUP: Hair Compositional Universal Prior for 3D Gaussian Avatars |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2507.19481 |