High-Fidelity Diffusion Face Swapping with ID-Constrained Facial Conditioning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: He, Dailan, Wang, Xiahong, Wang, Shulun, Song, Guanglu, Ma, Bingqi, Shao, Hao, Liu, Yu, Li, Hongsheng
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912971510251520
author He, Dailan
Wang, Xiahong
Wang, Shulun
Song, Guanglu
Ma, Bingqi
Shao, Hao
Liu, Yu
Li, Hongsheng
author_facet He, Dailan
Wang, Xiahong
Wang, Shulun
Song, Guanglu
Ma, Bingqi
Shao, Hao
Liu, Yu
Li, Hongsheng
contents Face swapping aims to seamlessly transfer a source facial identity onto a target while preserving target attributes such as pose and expression. Diffusion models, known for their superior generative capabilities, have recently shown promise in advancing face-swapping quality. This paper addresses two key challenges in diffusion-based face swapping: the prioritized preservation of identity over target attributes and the inherent conflict between identity and attribute conditioning. To tackle these issues, we introduce an identity-constrained attribute-tuning framework for face swapping that first ensures identity preservation and then fine-tunes for attribute alignment, achieved through a decoupled condition injection. We further enhance fidelity by incorporating identity and adversarial losses in a post-training refinement stage. Our proposed identity-constrained diffusion-based face-swapping model outperforms existing methods in both qualitative and quantitative evaluations, demonstrating superior identity similarity and attribute consistency, achieving a new state-of-the-art performance in high-fidelity face swapping.
format Preprint
id arxiv_https___arxiv_org_abs_2503_22179
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle High-Fidelity Diffusion Face Swapping with ID-Constrained Facial Conditioning
He, Dailan
Wang, Xiahong
Wang, Shulun
Song, Guanglu
Ma, Bingqi
Shao, Hao
Liu, Yu
Li, Hongsheng
Computer Vision and Pattern Recognition
Face swapping aims to seamlessly transfer a source facial identity onto a target while preserving target attributes such as pose and expression. Diffusion models, known for their superior generative capabilities, have recently shown promise in advancing face-swapping quality. This paper addresses two key challenges in diffusion-based face swapping: the prioritized preservation of identity over target attributes and the inherent conflict between identity and attribute conditioning. To tackle these issues, we introduce an identity-constrained attribute-tuning framework for face swapping that first ensures identity preservation and then fine-tunes for attribute alignment, achieved through a decoupled condition injection. We further enhance fidelity by incorporating identity and adversarial losses in a post-training refinement stage. Our proposed identity-constrained diffusion-based face-swapping model outperforms existing methods in both qualitative and quantitative evaluations, demonstrating superior identity similarity and attribute consistency, achieving a new state-of-the-art performance in high-fidelity face swapping.
title High-Fidelity Diffusion Face Swapping with ID-Constrained Facial Conditioning
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2503.22179