Share

Authors: Ming Liu,Yukang Ding,Min Xia,Xiao Liu,Errui Ding,Wangmeng Zuo,Shilei Wen
Where published: CVPR 2019 6
ArXiv: 1904.09709
Document:  PDF  DOI 
Artifact development version: GitHub
Abstract URL: http://arxiv.org/abs/1904.09709v1


Arbitrary attribute editing generally can be tackled by incorporating encoder-decoder and generative adversarial networks. However, the bottleneck layer in encoder-decoder usually gives rise to blurry and low quality editing result. And adding skip connections improves image quality at the cost of weakened attribute manipulation ability. Moreover, existing methods exploit target attribute vector to guide the flexible translation to desired target domain. In this work, we suggest to address these issues from selective transfer perspective. Considering that specific editing task is certainly only related to the changed attributes instead of all target attributes, our model selectively takes the difference between target and source attribute vectors as input. Furthermore, selective transfer units are incorporated with encoder-decoder to adaptively select and modify encoder feature for enhanced attribute editing. Experiments show that our method (i.e., STGAN) simultaneously improves attribute manipulation accuracy as well as perception quality, and performs favorably against state-of-the-arts in arbitrary facial attribute editing and season translation.

Relevant initiatives   Hide

Comments   Hide

Please log in to add your comments!