# Learning Domain Agnostic Latent Embeddings of 3D Faces for Zero-shot Animal Expression Transfer

arXiv: https://arxiv.org/abs/2601.06484 · HTML: https://mlsanity.com/paper/2601.06484/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 14 of its 25 references that are in the map.
- First posted on arXiv 10 Jan 2026.

## Builds on (most cited first, 14 of 14)

- [First Order Motion Model for Image Animation](https://mlsanity.com/paper/2003.00196/) (2020)
- [Face2Face: Real-time Face Capture and Reenactment of RGB Videos](https://mlsanity.com/paper/2007.14808/) (2020)
- [3D Menagerie: Modeling the 3D shape and pose of animals](https://mlsanity.com/paper/1611.07700/) (2016)
- [DiffusionNet: Discretization Agnostic Learning on Surfaces](https://mlsanity.com/paper/2012.00888/) (2020)
- [Learning Formation of Physically-Based Face Attributes](https://mlsanity.com/paper/2004.03458/) (2020)
- [Learning Detailed Face Reconstruction from a Single Image](https://mlsanity.com/paper/1611.05053/) (2016)
- [Neural Jacobian Fields: Learning Intrinsic Mappings of Arbitrary Meshes](https://mlsanity.com/paper/2205.02904/) (2022)
- [Neural Face Rigging for Animating and Retargeting Facial Meshes in the Wild](https://mlsanity.com/paper/2305.08296/) (2023)
- [Facial Expression Retargeting from Human to Avatar Made Easy](https://mlsanity.com/paper/2008.05110/) (2020)
- [OT-Talk: Animating 3D Talking Head with Optimal Transportation](https://mlsanity.com/paper/2505.01932/) (2025)
- [LeGO: Leveraging a Surface Deformation Network for Animatable Stylized Face Generation with One Example](https://mlsanity.com/paper/2403.15227/) (2024)
- [Neural Geometry Image-Based Representations with Optimal Transport (OT)](https://mlsanity.com/paper/2511.18679/) (2025)
- [Inverse Rendering for High-Genus Surface Meshes from Multi-View Images](https://mlsanity.com/paper/2511.18680/) (2025)
- [Hierarchical GraphCut Phase Unwrapping based on Invariance of Diffeomorphisms Framework](https://mlsanity.com/paper/2511.18682/) (2025)

## Abstract (arXiv)

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.