APPLE: Attribute-Preserving Pseudo-Labeling for Diffusion-Based Face Swapping

TL;DR

APPLE introduces a diffusion-based teacher-student framework for face swapping that significantly improves attribute preservation, including skin tone, illumination, and makeup, while maintaining competitive identity transfer.

Contribution

The paper proposes a novel attribute-preserving pseudo-labeling method with a teacher-student diffusion framework for improved face swapping quality.

Findings

Achieves state-of-the-art attribute preservation in face swapping.

Maintains competitive identity transfer performance.

Utilizes a conditional deblurring and attribute-aware inversion scheme.

Abstract

Face swapping aims to transfer the identity of a source face onto a target face while preserving target-specific attributes such as pose, expression, lighting, skin tone, and makeup. However, since real ground truth for face swapping is unavailable, achieving both accurate identity transfer and high-quality attribute preservation remains challenging. Recent diffusion-based approaches attempt to improve visual fidelity through conditional inpainting on masked target images, but the masked condition removes crucial appearance cues, resulting in plausible yet misaligned attributes. To address this limitation, we propose APPLE (Attribute-Preserving Pseudo-Labeling), a fully diffusion-based teacher-student framework for attribute-preserving face swapping. Our approach introduces a teacher design to produce pseudo-labels aligned with the target attributes through (1) a conditional deblurring formulation that improves the preservation of global attributes such as skin tone and illumination, and (2) an attribute-aware inversion scheme that further enhances fine-grained attribute preservation such as makeup. APPLE conditions the student on clean pseudo-labels rather than degraded masked inputs, enabling more faithful attribute preservation. As a result, APPLE achieves state-of-the-art performance in attribute preservation while maintaining competitive identity transferability.