Gaussian Wardrobe: Compositional 3D Gaussian Avatars for Free-Form Virtual Try-On
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866918372300554240 |
|---|---|
| author | Chen, Zhiyi Ho, Hsuan-I Jiang, Tianjian Song, Jie Kaufmann, Manuel Guo, Chen |
| author_facet | Chen, Zhiyi Ho, Hsuan-I Jiang, Tianjian Song, Jie Kaufmann, Manuel Guo, Chen |
| contents | We introduce Gaussian Wardrobe, a novel framework to digitalize compositional 3D neural avatars from multi-view videos. Existing methods for 3D neural avatars typically treat the human body and clothing as an inseparable entity. However, this paradigm fails to capture the dynamics of complex free-form garments and limits the reuse of clothing across different individuals. To overcome these problems, we develop a novel, compositional 3D Gaussian representation to build avatars from multiple layers of free-form garments. The core of our method is decomposing neural avatars into bodies and layers of shape-agnostic neural garments. To achieve this, our framework learns to disentangle each garment layer from multi-view videos and canonicalizes it into a shape-independent space. In experiments, our method models photorealistic avatars with high-fidelity dynamics, achieving new state-of-the-art performance on novel pose synthesis benchmarks. In addition, we demonstrate that the learned compositional garments contribute to a versatile digital wardrobe, enabling a practical virtual try-on application where clothing can be freely transferred to new subjects. Project page: https://ait.ethz.ch/gaussianwardrobe |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_04290 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Gaussian Wardrobe: Compositional 3D Gaussian Avatars for Free-Form Virtual Try-On Chen, Zhiyi Ho, Hsuan-I Jiang, Tianjian Song, Jie Kaufmann, Manuel Guo, Chen Computer Vision and Pattern Recognition Graphics We introduce Gaussian Wardrobe, a novel framework to digitalize compositional 3D neural avatars from multi-view videos. Existing methods for 3D neural avatars typically treat the human body and clothing as an inseparable entity. However, this paradigm fails to capture the dynamics of complex free-form garments and limits the reuse of clothing across different individuals. To overcome these problems, we develop a novel, compositional 3D Gaussian representation to build avatars from multiple layers of free-form garments. The core of our method is decomposing neural avatars into bodies and layers of shape-agnostic neural garments. To achieve this, our framework learns to disentangle each garment layer from multi-view videos and canonicalizes it into a shape-independent space. In experiments, our method models photorealistic avatars with high-fidelity dynamics, achieving new state-of-the-art performance on novel pose synthesis benchmarks. In addition, we demonstrate that the learned compositional garments contribute to a versatile digital wardrobe, enabling a practical virtual try-on application where clothing can be freely transferred to new subjects. Project page: https://ait.ethz.ch/gaussianwardrobe |
| title | Gaussian Wardrobe: Compositional 3D Gaussian Avatars for Free-Form Virtual Try-On |
| topic | Computer Vision and Pattern Recognition Graphics |
| url | https://arxiv.org/abs/2603.04290 |