Segmentation-Reconstruction-Guided Facial Image De-occlusion

Xiangnan Yin, Di Huang, Zehua Fu, Yunhong Wang, Liming Luke Chen
{"title":"Segmentation-Reconstruction-Guided Facial Image De-occlusion","authors":"Xiangnan Yin, Di Huang, Zehua Fu, Yunhong Wang, Liming Luke Chen","doi":"10.1109/FG57933.2023.10042570","DOIUrl":null,"url":null,"abstract":"Occlusions are very common in face images in the wild, leading to the degraded performance of face-related tasks. Although much effort has been devoted to removing occlusions from face images, the varying shapes and textures of occlusions still challenge the robustness of current methods. As a result, current methods either rely on manual occlusion masks or only apply to specific occlusions. This paper proposes a novel face de-occlusion model based on face segmentation and 3D face reconstruction, which is robust to arbitrary kinds of face occlusions. The proposed model consists of a 3D face reconstruction module, a face segmentation module, and an image generation module. With the face prior and the occlusion mask predicted by the first two, respectively, the image generation module can faithfully recover the missing facial textures. To supervise the training, we further build a large occlusion dataset, with both manually labeled and synthetic occlusions. Qualitative and quantitative results demonstrate the effectiveness and robustness of the proposed method.","PeriodicalId":318766,"journal":{"name":"2023 IEEE 17th International Conference on Automatic Face and Gesture Recognition (FG)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2021-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"3","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2023 IEEE 17th International Conference on Automatic Face and Gesture Recognition (FG)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/FG57933.2023.10042570","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 3

Abstract

Occlusions are very common in face images in the wild, leading to the degraded performance of face-related tasks. Although much effort has been devoted to removing occlusions from face images, the varying shapes and textures of occlusions still challenge the robustness of current methods. As a result, current methods either rely on manual occlusion masks or only apply to specific occlusions. This paper proposes a novel face de-occlusion model based on face segmentation and 3D face reconstruction, which is robust to arbitrary kinds of face occlusions. The proposed model consists of a 3D face reconstruction module, a face segmentation module, and an image generation module. With the face prior and the occlusion mask predicted by the first two, respectively, the image generation module can faithfully recover the missing facial textures. To supervise the training, we further build a large occlusion dataset, with both manually labeled and synthetic occlusions. Qualitative and quantitative results demonstrate the effectiveness and robustness of the proposed method.
分割-重建引导的人脸图像去遮挡
遮挡在野外人脸图像中非常常见,导致人脸相关任务的性能下降。尽管人们在去除人脸图像中的遮挡方面做了很多努力,但遮挡物形状和纹理的变化仍然对现有方法的鲁棒性提出了挑战。因此,当前的方法要么依赖于手动遮挡,要么只适用于特定的遮挡。提出了一种基于人脸分割和三维人脸重建的人脸去遮挡模型,该模型对任意类型的人脸遮挡具有较强的鲁棒性。该模型由三维人脸重构模块、人脸分割模块和图像生成模块组成。利用前两者预测的人脸先验和遮挡遮挡,图像生成模块可以忠实地恢复缺失的人脸纹理。为了监督训练,我们进一步构建了一个大型遮挡数据集,其中包括手动标记和合成遮挡。定性和定量结果证明了该方法的有效性和鲁棒性。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信