Attribute-Driven Spontaneous Motion in Unpaired Image Translation

解决的问题

前人的做法:

Ÿ   Success of image translation methods mostly imposes the requirement of working on aligned or similar domains for texture or appearance transform.

Ÿ   The building blocks of these networks, such as convolution/deconvolution layers and activation functions, are spatially corresponding.

解决的问题:

大白话解释一段我的理解:

       非成对图像翻译,比如非笑脸图(小明,男)要翻译成笑脸图(小明,男)。

       输入网络的图,非笑脸图(小明,男)和笑脸图(大红唇的小红,女),经过一系列的convolution/deconvolution layers and activation functions,得到小明的五官信息和大红唇小红的笑信息(maybe 嘴角上扬图),重组以后得到,大红唇的笑脸小明。

       结果图中的大红唇可以看作artifacts or ghosting。

期望的效果:

具体策略:

SPM

 

RM

12个平行采样的残差块,对生成结果进行精细化。

Mask

Ÿ   3 deconvolutional layers to up-sample f into a 1-channel mask m, the same size as the input.

Ÿ   Sigmoid layer is used as the final activation layer to range the output mask in [0; 1].

Ÿ   a regularization term Lm to enforce sparsity of masks in L1-norm: 

实验详情

 

 实验效果:

 

 

 

posted @ 2020-02-20 17:57  皮卡皮卡妞  阅读(192)  评论(0编辑  收藏  举报