pith. sign in

arxiv: 1803.01837 · v1 · pith:A7VAFOL2new · submitted 2018-03-05 · 💻 cs.CV · cs.LG

ST-GAN: Spatial Transformer Generative Adversarial Networks for Image Compositing

classification 💻 cs.CV cs.LG
keywords imagespatialtransformeradversarialgenerativegeneratorgeometricimages
0
0 comments X
read the original abstract

We address the problem of finding realistic geometric corrections to a foreground object such that it appears natural when composited into a background image. To achieve this, we propose a novel Generative Adversarial Network (GAN) architecture that utilizes Spatial Transformer Networks (STNs) as the generator, which we call Spatial Transformer GANs (ST-GANs). ST-GANs seek image realism by operating in the geometric warp parameter space. In particular, we exploit an iterative STN warping scheme and propose a sequential training strategy that achieves better results compared to naive training of a single generator. One of the key advantages of ST-GAN is its applicability to high-resolution images indirectly since the predicted warp parameters are transferable between reference frames. We demonstrate our approach in two applications: (1) visualizing how indoor furniture (e.g. from product images) might be perceived in a room, (2) hallucinating how accessories like glasses would look when matched with real portraits.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.