UniBioTransfer: A Unified Framework for Multiple Biometrics Transfer

2026-03-20

AI Summary

Existing face generation methods often rely on task-specific models, limiting their generalizability, while unified modeling faces challenges due to data scarcity and cross-task conflicts. This work proposes UniBioTransfer—the first unified multi-biometric transfer framework—capable of handling standard face swapping, facial expression reenactment, and deformable attributes such as hairstyle and head shape, with zero-shot or fine-tuned generalization to unseen tasks like lip, eye, and eyewear manipulation. To model dynamic spatial attributes, the method introduces a swap-based corruption mechanism and employs a BioMoE (Biometric Mixture-of-Experts) architecture combined with a two-stage training strategy to effectively decouple task-specific knowledge and mitigate interference. Experiments demonstrate that UniBioTransfer outperforms both existing unified and specialized models across multiple tasks, exhibiting superior performance, generalization capability, and scalability.

Technology Category

• Computer Vision: Biometrics, Face, Gesture & Pose
• Machine Learning: Transfer, Domain Adaptation, Multi-Task Learning
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Deepface generation has traditionally followed a task-driven paradigm, where distinct tasks (e.g., face transfer and hair transfer) are addressed by task-specific models. Nevertheless, this single-task setting severely limits model generalization and scalability. A unified model capable of solving multiple deepface generation tasks in a single pass represents a promising and practical direction, yet remains challenging due to data scarcity and cross-task conflicts arising from heterogeneous attribute transformations. To this end, we propose UniBioTransfer, the first unified framework capable of handling both conventional deepface tasks (e.g., face transfer and face reenactment) and shape-varying transformations (e.g., hair transfer and head transfer). Besides, UniBioTransfer naturally generalizes to unseen tasks, like lip, eye, and glasses transfer, with minimal fine-tuning. Generally, UniBioTransfer addresses data insufficiency in multi-task generation through a unified data construction strategy, including a swapping-based corruption mechanism designed for spatially dynamic attributes like hair. It further mitigates cross-task interference via an innovative BioMoE, a mixture-of-experts based model coupled with a novel two-stage training strategy that effectively disentangles task-specific knowledge. Extensive experiments demonstrate the effectiveness, generalization, and scalability of UniBioTransfer, outperforming both existing unified models and task-specific methods across a wide range of deepface generation tasks. Project page is at https://scy639.github.io/UniBioTransfer.github.io/

Problem

• deepface generation
• unified framework
• multi-task learning
• cross-task conflict
• data scarcity

Innovation

• Unified Framework
• Mixture-of-Experts (MoE)
• Multi-task Face Generation
• Data Construction Strategy
• Cross-task Disentanglement