Face Attribute Invertion
This addresses face attribute manipulation for computer vision applications, but appears incremental as it builds on existing GAN-based approaches.
The paper tackles the problem of manipulating human facial images between domains by proposing a novel self-perception method based on GANs for automatic face attribute inversion, achieving stable training and preservation of finer details in original face images.
Manipulating human facial images between two domains is an important and interesting problem. Most of the existing methods address this issue by applying two generators or one generator with extra conditional inputs. In this paper, we proposed a novel self-perception method based on GANs for automatical face attribute inverse. The proposed method takes face images as inputs and employs only one single generator without being conditioned on other inputs. Profiting from the multi-loss strategy and modified U-net structure, our model is quite stable in training and capable of preserving finer details of the original face images.