Harnessing semantic segmentation masks for accurate facial attribute editing. (24th April 2020)

• Record Type: Journal Article
• Authors: Chen, Peng; Xiao, Qi; Xu, Jian; Dong, Xiaoli; Sun, Linjun; Li, Weijun; Ning, Xin; Wang, Guojun; Chen, Ziheng
• Is Part Of: Concurrency and computation. Volume 34:Number 12(2022)
• Page Start: n/a
• Page End: n/a
• Publication Date: 2020-04-24
• Subjects: accurate facial attribute editing -- adversarial learning -- generative adversarial network -- semantic segmentation network; Parallel processing (Electronic computers) -- Periodicals; Parallel computers -- Periodicals; 004.35
• DOI: 10.1002/cpe.5798
• Languages: English
• ISSNs: 1532-0626

Abstract

Summary: In recent years, with the rapid development of adversarial learning technology, facial attribute editing has made great success in a number of areas. Realistic visual effect, invariant identity information, and accurate editing area are the three key issues of facial attribute editing. Unfortunately, most researches focus on the former two problems. However, lack of awareness of the accurate editing area in the task is the main reason for damaging attribute‐irrelevant details. To address this issue, this article proposes a novel facial attribute editing algorithm—a generative adversarial network (GAN) with semantic masks—from the perspective of editing location accuracy. By generating the mask with respect to attribute‐related areas, the semantic segmentation network can only constrain the manipulation in the target region while not harming any attribute‐irrelevant details. The GAN is then combined with the semantic segmentation network to formulate the entire framework, which is referred to as SM‐GAN. Extensive experiments on the public datasets CelebA and LFWA prove that the presented method can not only ensure that the attribute manipulation is realistic, but also allow attribute‐irrelevant regions to remain unchanged. Moreover, it can also simultaneously edit multiple facial attributes.