SARA: Controllable Makeup Transfer with Spatial Alignment and Region-Adaptive Normalization

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Zhong, Xiaojing, Huang, Xinyi, Wu, Zhonghua, Lin, Guosheng, Wu, Qingyao
Natura: Preprint
Pubblicazione: 2023
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866911882918494208
author Zhong, Xiaojing
Huang, Xinyi
Wu, Zhonghua
Lin, Guosheng
Wu, Qingyao
author_facet Zhong, Xiaojing
Huang, Xinyi
Wu, Zhonghua
Lin, Guosheng
Wu, Qingyao
contents Makeup transfer is a process of transferring the makeup style from a reference image to the source images, while preserving the source images' identities. This technique is highly desirable and finds many applications. However, existing methods lack fine-level control of the makeup style, making it challenging to achieve high-quality results when dealing with large spatial misalignments. To address this problem, we propose a novel Spatial Alignment and Region-Adaptive normalization method (SARA) in this paper. Our method generates detailed makeup transfer results that can handle large spatial misalignments and achieve part-specific and shade-controllable makeup transfer. Specifically, SARA comprises three modules: Firstly, a spatial alignment module that preserves the spatial context of makeup and provides a target semantic map for guiding the shape-independent style codes. Secondly, a region-adaptive normalization module that decouples shape and makeup style using per-region encoding and normalization, which facilitates the elimination of spatial misalignments. Lastly, a makeup fusion module blends identity features and makeup style by injecting learned scale and bias parameters. Experimental results show that our SARA method outperforms existing methods and achieves state-of-the-art performance on two public datasets.
format Preprint
id arxiv_https___arxiv_org_abs_2311_16828
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle SARA: Controllable Makeup Transfer with Spatial Alignment and Region-Adaptive Normalization
Zhong, Xiaojing
Huang, Xinyi
Wu, Zhonghua
Lin, Guosheng
Wu, Qingyao
Computer Vision and Pattern Recognition
Makeup transfer is a process of transferring the makeup style from a reference image to the source images, while preserving the source images' identities. This technique is highly desirable and finds many applications. However, existing methods lack fine-level control of the makeup style, making it challenging to achieve high-quality results when dealing with large spatial misalignments. To address this problem, we propose a novel Spatial Alignment and Region-Adaptive normalization method (SARA) in this paper. Our method generates detailed makeup transfer results that can handle large spatial misalignments and achieve part-specific and shade-controllable makeup transfer. Specifically, SARA comprises three modules: Firstly, a spatial alignment module that preserves the spatial context of makeup and provides a target semantic map for guiding the shape-independent style codes. Secondly, a region-adaptive normalization module that decouples shape and makeup style using per-region encoding and normalization, which facilitates the elimination of spatial misalignments. Lastly, a makeup fusion module blends identity features and makeup style by injecting learned scale and bias parameters. Experimental results show that our SARA method outperforms existing methods and achieves state-of-the-art performance on two public datasets.
title SARA: Controllable Makeup Transfer with Spatial Alignment and Region-Adaptive Normalization
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2311.16828