StyleYourSmile: Cross-Domain Face Retargeting Without Paired Multi-Style Data

TL;DR

StyleYourSmile is a novel one-shot cross-domain face retargeting method that uses disentangled control signals and a diffusion model, eliminating the need for curated multi-style paired data and achieving high fidelity across diverse domains.

Contribution

It introduces a new framework combining data augmentation, dual-encoder disentanglement, and diffusion models for cross-domain face retargeting without multi-style paired datasets.

Findings

Achieves superior identity preservation across domains

Demonstrates high retargeting fidelity in diverse visual domains

Eliminates need for test-time optimization or fine-tuning

Abstract

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.