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

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Kang, Jiwon, Choi, Yeji, Lee, JoungBin, Jang, Wooseok, Choi, Jinhyeok, Kang, Taekeun, Park, Yongjae, Kim, Myungin, Kim, Seungryong
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866915900006858752
author Kang, Jiwon
Choi, Yeji
Lee, JoungBin
Jang, Wooseok
Choi, Jinhyeok
Kang, Taekeun
Park, Yongjae
Kim, Myungin
Kim, Seungryong
author_facet Kang, Jiwon
Choi, Yeji
Lee, JoungBin
Jang, Wooseok
Choi, Jinhyeok
Kang, Taekeun
Park, Yongjae
Kim, Myungin
Kim, Seungryong
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2601_15288
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle APPLE: Attribute-Preserving Pseudo-Labeling for Diffusion-Based Face Swapping
Kang, Jiwon
Choi, Yeji
Lee, JoungBin
Jang, Wooseok
Choi, Jinhyeok
Kang, Taekeun
Park, Yongjae
Kim, Myungin
Kim, Seungryong
Computer Vision and Pattern Recognition
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.
title APPLE: Attribute-Preserving Pseudo-Labeling for Diffusion-Based Face Swapping
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2601.15288