[知也无涯]GAN对人脸算法的影响

红绣被,两两间鸳鸯。不是鸟中偏爱尔,为缘交颈睡南塘。全胜薄情郎。

看到一篇GAN对人脸图像算法的影响,决心学习一个。

人脸检测

这也是我最关注的模块。文章推荐了极小面部区域人脸识别Finding tiny faces in the wild with generative adversarial network

遮挡人脸恢复与姿态仿真

姿态仿真其实和遮挡人脸是一类问题,就是对非规则化的输入进行判断。文章推荐了Towards large-pose face frontalization in the wild

年龄与表情仿真

这个在娱乐方面应用很广泛。之前爆火的faceU属于此类。文章的推荐是Face aging with conditional generative adversarial networksGeometry guided adversarial facial expression synthesis[C]//2018 ACM Multimedia Conference on Multimedia Conference

换脸与换脸检测

deepfake在2017年大火并引起广泛针对技术合法性方面的讨论,时至今日更加受欢迎的研究方向是换脸检测。文章推荐的两篇文章均是检测算法。我找到一篇综述Deep Learning for Deepfakes Creation and Detection。文章的推荐是Deepfakes: a new threat to face recognition? assessment and detectionLearning to Detect Manipulated Facial Images

人脸美颜

这是国内很成熟的技术了,目前比较火的方向是妆容迁移。推荐Beautygan: Instance-level facial makeup transfer with deep generative adversarial networkunsupervised generative attentional networks with adaptive layer-instance normalization for image-to-image translation

posted @ 2019-12-14 21:25  ziangzhang  阅读(438)  评论(0)    收藏  举报

唯乐呵是图<\p>