AttentionGAN: Unpaired Image-to-Image Translation using Attention-Guided
Generative Adversarial Networks
release_rhrln4kljvcubmjxgrl6wmuz2u
by
Hao Tang and Hong Liu and Dan Xu and Philip H.S. Torr and Nicu Sebe
2019
Abstract
State-of-the-art methods in the unpaired image-to-image translation are
capable of learning a mapping from a source domain to a target domain with
unpaired image data. Though the existing methods have achieved promising
results, they still produce unsatisfied artifacts, being able to convert
low-level information while limited in transforming high-level semantics of
input images. One possible reason is that generators do not have the ability to
perceive the most discriminative semantic parts between the source and target
domains, thus making the generated images low quality. In this paper, we
propose a new Attention-Guided Generative Adversarial Networks (AttentionGAN)
for the unpaired image-to-image translation task. AttentionGAN can identify the
most discriminative semantic objects and minimize changes of unwanted parts for
semantic manipulation problems without using extra data and models. The
attention-guided generators in AttentionGAN are able to produce attention masks
via a built-in attention mechanism, and then fuse the generation output with
the attention masks to obtain high-quality target images. Accordingly, we also
design a novel attention-guided discriminator which only considers attended
regions. Extensive experiments are conducted on several generative tasks,
demonstrating that the proposed model is effective to generate sharper and more
realistic images compared with existing competitive models. The source code for
the proposed AttentionGAN is available at
https://github.com/Ha0Tang/AttentionGAN.
In text/plain
format
Archived Files and Locations
application/pdf 9.9 MB
file_n2vvhsrwdjcfxoaffp7ib57qy4
|
arxiv.org (repository) web.archive.org (webarchive) |
1911.11897v1
access all versions, variants, and formats of this works (eg, pre-prints)