CASIA OpenIR  > 智能感知与计算
Towards High Fidelity Face Frontalization in the Wild
Cao, Jie1,2; Hu, Yibo1,2; Zhang, Hongwen1,2; He, Ran1,2; Sun, Zhenan1,2
发表期刊International Journal of Computer Vision
2019
卷号128期号:1页码:1485–1504
摘要

Face frontalization refers to the process of synthesizing the frontal view of a face from a given profile. Due to self-occlusion and appearance distortion in the wild, it is extremely challenging to recover faithful high-resolution results meanwhile preserve texture details. This paper proposes a high fidelity pose in-variant model (HF-PIM) to produce photographic and identity-preserving results. HF-PIM frontalizes the profiles through a novel texture fusion warping procedure and leverages a dense correspondence field to bind the 2D and 3D surface spaces. We decompose the prerequisite of warping into dense correspondence field estimation and facial texture map recovering, which are both well addressed by deep networks. Different from those reconstruction methods relying on 3D data, we also propose adversarial residual dictionary learning to supervise facial texture map recovering with only monocular images. Furthermore, a multi-perception guided loss is proposed to address the practical misalignment between the ground truth frontal and profile faces, allowing HF-PIM to effectively utilize multiple images during training. Quantitative and qualitative evaluations on five controlled and uncontrolled databases show that the proposed method not only boosts the performance of pose-invariant face recognition but also improves the visual quality of high-resolution frontalization appearances.

关键词Face frontalization Realistic face generation Pose-invariant face recognition
收录类别SCI
语种英语
七大方向——子方向分类生物特征识别
文献类型期刊论文
条目标识符http://ir.ia.ac.cn/handle/173211/44303
专题智能感知与计算
通讯作者Sun, Zhenan
作者单位1.中国科学院自动化研究所
2.中国科学院大学
第一作者单位中国科学院自动化研究所
通讯作者单位中国科学院自动化研究所
推荐引用方式
GB/T 7714
Cao, Jie,Hu, Yibo,Zhang, Hongwen,et al. Towards High Fidelity Face Frontalization in the Wild[J]. International Journal of Computer Vision,2019,128(1):1485–1504.
APA Cao, Jie,Hu, Yibo,Zhang, Hongwen,He, Ran,&Sun, Zhenan.(2019).Towards High Fidelity Face Frontalization in the Wild.International Journal of Computer Vision,128(1),1485–1504.
MLA Cao, Jie,et al."Towards High Fidelity Face Frontalization in the Wild".International Journal of Computer Vision 128.1(2019):1485–1504.
条目包含的文件 下载所有文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
Cao 等。 - 2020 - Towa(3816KB)期刊论文作者接受稿开放获取CC BY-NC-SA浏览 下载
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Cao, Jie]的文章
[Hu, Yibo]的文章
[Zhang, Hongwen]的文章
百度学术
百度学术中相似的文章
[Cao, Jie]的文章
[Hu, Yibo]的文章
[Zhang, Hongwen]的文章
必应学术
必应学术中相似的文章
[Cao, Jie]的文章
[Hu, Yibo]的文章
[Zhang, Hongwen]的文章
相关权益政策
暂无数据
收藏/分享
文件名: Cao 等。 - 2020 - Towards high fidelity face frontalization in the w.pdf
格式: Adobe PDF
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。