StyleYourSmile: Cross-Domain Face Retargeting Without Paired Multi-Style Data
This addresses the challenge of disentangling identity and style in face retargeting for applications like animation or virtual avatars, though it appears incremental in method.
The paper tackles the problem of cross-domain face retargeting by introducing StyleYourSmile, a method that eliminates the need for curated multi-style paired data, achieving superior identity preservation and retargeting fidelity across domains.
Cross-domain face retargeting requires disentangled control over identity, expressions, and domain-specific stylistic attributes. Existing methods, typically trained on real-world faces, either fail to generalize across domains, need test-time optimizations, or require fine-tuning with carefully curated multi-style datasets to achieve domain-invariant identity representations. In this work, we introduce \textit{StyleYourSmile}, a novel one-shot cross-domain face retargeting method that eliminates the need for curated multi-style paired data. We propose an efficient data augmentation strategy alongside a dual-encoder framework, for extracting domain-invariant identity cues and capturing domain-specific stylistic variations. Leveraging these disentangled control signals, we condition a diffusion model to retarget facial expressions across domains. Extensive experiments demonstrate that \textit{StyleYourSmile} achieves superior identity preservation and retargeting fidelity across a wide range of visual domains.