Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2601.06484 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917194377461760 |
|---|---|
| author | Wang, Yue Amadi, Lawrence Gao, Xiang Chen, Yazheng Liu, Yuanpeng Lu, Ning Gu, Xianfeng |
| author_facet | Wang, Yue Amadi, Lawrence Gao, Xiang Chen, Yazheng Liu, Yuanpeng Lu, Ning Gu, Xianfeng |
| contents | We present a zero-shot framework for transferring human facial expressions to 3D animal face meshes. Our method combines intrinsic geometric descriptors (HKS/WKS) with a mesh-agnostic latent embedding that disentangles facial identity and expression. The ID latent space captures species-independent facial structure, while the expression latent space encodes deformation patterns that generalize across humans and animals. Trained only with human expression pairs, the model learns the embeddings, decoupling, and recoupling of cross-identity expressions, enabling expression transfer without requiring animal expression data. To enforce geometric consistency, we employ Jacobian loss together with vertex-position and Laplacian losses. Experiments show that our approach achieves plausible cross-species expression transfer, effectively narrowing the geometric gap between human and animal facial shapes. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_06484 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Learning Domain Agnostic Latent Embeddings of 3D Faces for Zero-shot Animal Expression Transfer Wang, Yue Amadi, Lawrence Gao, Xiang Chen, Yazheng Liu, Yuanpeng Lu, Ning Gu, Xianfeng Computer Vision and Pattern Recognition Artificial Intelligence We present a zero-shot framework for transferring human facial expressions to 3D animal face meshes. Our method combines intrinsic geometric descriptors (HKS/WKS) with a mesh-agnostic latent embedding that disentangles facial identity and expression. The ID latent space captures species-independent facial structure, while the expression latent space encodes deformation patterns that generalize across humans and animals. Trained only with human expression pairs, the model learns the embeddings, decoupling, and recoupling of cross-identity expressions, enabling expression transfer without requiring animal expression data. To enforce geometric consistency, we employ Jacobian loss together with vertex-position and Laplacian losses. Experiments show that our approach achieves plausible cross-species expression transfer, effectively narrowing the geometric gap between human and animal facial shapes. |
| title | Learning Domain Agnostic Latent Embeddings of 3D Faces for Zero-shot Animal Expression Transfer |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2601.06484 |