arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1902.04202cs.CVcs.CYcs.LG
收藏

去身份化不丢面子

De-identification without losing faces

University at Albany, State University of New York(纽约州立大学奥尔巴尼分校)

Yuezun Li, Siwei Lyu

摘要:

用于计算机视觉的深度学习模型的训练需要来自真实世界的大型图像或视频数据集。通常,在收集此类数据集时,我们需要保护图像或视频中捕获的人的隐私,同时仍然保留有用的属性,如面部表情。在这项工作中,我们描述了一种新的人脸去识别方法,可以保持基本的面部属性的脸,同时隐藏身份。我们的方法利用了人脸属性转移模型的最新进展,同时保持了较高的视觉质量。我们的方法不是改变原始面孔的因素或完全合成面孔,而是使用经过训练的面部属性转移模型将非身份相关的面部属性映射到捐赠者的面部,捐赠者是少数(通常为2到3个)同意的受试者。使用供体的面部确保合成面部的自然外观,同时确保合成面部的身份被改变。另一方面,FATM将捐赠者的面部属性与原始面部的面部属性混合以使合成面部的外观多样化。在多组图像和视频上的实验结果证明了该算法的有效性。

英文摘要:

Training of deep learning models for computer vision requires large image or video datasets from real world. Often, in collecting such datasets, we need to protect the privacy of the people captured in the images or videos, while still preserve the useful attributes such as facial expressions. In this work, we describe a new face de-identification method that can preserve essential facial attributes in the faces while concealing the identities. Our method takes advantage of the recent advances in face attribute transfer models, while maintaining a high visual quality. Instead of changing factors of the original faces or synthesizing faces completely, our method use a trained facial attribute transfer model to map non-identity related facial attributes to the face of donors, who are a small number (usually 2 to 3) of consented subjects. Using the donors' faces ensures that the natural appearance of the synthesized faces, while ensuring the identity of the synthesized faces are changed. On the other hand, the FATM blends the donors' facial attributes to those of the original faces to diversify the appearance of the synthesized faces. Experimental results on several sets of images and videos demonstrate the effectiveness of our face de-ID algorithm.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑