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

Chen-Hsuan Lin, Ersin Yumer, Oliver Wang, Eli Shechtman, Simon Lucey
2018 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition  
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
more » ... 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.
doi:10.1109/cvpr.2018.00985 dblp:conf/cvpr/LinYWSL18 fatcat:jvbq57cktjhgpngurrchjitb4e