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

Chen-Hsuan Lin, Ersin Yumer, Oliver Wang, Eli Shechtman, Simon Lucey; The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018, pp. 9455-9464

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.

Related Material


[pdf] [arXiv]
[bibtex]
@InProceedings{Lin_2018_CVPR,
author = {Lin, Chen-Hsuan and Yumer, Ersin and Wang, Oliver and Shechtman, Eli and Lucey, Simon},
title = {ST-GAN: Spatial Transformer Generative Adversarial Networks for Image Compositing},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2018}
}