评论
打印
As virtual makeup apps gain popularity, Chinese developers are working on a way to remove makeup from over-edited photos.
随着虚拟化妆应用越来越流行，我国开发者正在研究为过度编辑的照片卸妆的途径。
Tencent Youtu Lab, an artificial intelligence research lab under tech giant Tencent, released a new algorithm that can reverse over-edited deceiving pictures.
科技巨头腾讯旗下的人工智能研究实验室腾讯优图实验室发布了一种可以将过度编辑、有欺骗性的图片复原的新算法。
Dubbed "makeup-go," the algorithm is claimed to be the first of its kind in the world, and it focuses on tackling the two issues of skin smoothing and skin color change.
这种名为“一键卸妆”的算法，声称是世界上首个该类型的算法，主要解决磨皮和皮肤调色这两个问题。
One of the difficulties mentioned by the lab is that every virtual makeup software performs quite differently, which make it impossible to learn all operations that can smooth skin, suppress wrinkle and freckle, and adjust tone.
实验室提及的困难之一是，每一款虚拟化妆软件的运行不尽相同，使其不可能学会磨皮、平皱、祛斑和调色的所有操作。
Therefore, the team designed a new algorithm to reverse pictures "blindly."
因此，该团队设计了一种新算法来“盲复原”图片。
Also, instead of directly regressing the pictures towards the unedited version, the network regresses levels of principal components of the edited parts separately. As a result, subtle detail information won't be ignored.
另外，该系统并不是直接将照片转化为未经编辑的版本，而是分步骤分层次将每个编辑部分逐个还原。这样，那些细微的细节就不会被忽略了。
Makeup-go doesn't handle geometric face-lifting at the moment, the team said in the paper.
该团队在文件中写道，这个软件目前还无法处理面部整容问题。
