Cross-View Image Synthesis Using Conditional Gans
Abstract
Learning to generate natural scenes has always been a challenging task in computer vision. It is even more painstaking when the generation is conditioned on images with drastically different views. This is mainly because understanding, corresponding, and transforming appearance and semantic information across the views is not trivial. In this paper, we attempt to solve the novel problem of cross-view image synthesis, aerial to street-view and vice versa, using conditional generative adversarial networks (cGAN). Two new architectures called Crossview Fork (X-Fork) and Crossview Sequential (X-Seq) are proposed to generate scenes with resolutions of 64Ã - 64 and 256Ã - 256 pixels. X-Fork architecture has a single discriminator and a single generator. The generator hallucinates both the image and its semantic segmentation in the target view. X-Seq architecture utilizes two cGANs. The first one generates the target image which is subsequently fed to the second cGAN for generating its corresponding semantic segmentation map. The feedback from the second cGAN helps the first cGAN generate sharper images. Both of our proposed architectures learn to generate natural images as well as their semantic segmentation maps. The proposed methods show that they are able to capture and maintain the true semantics of objects in source and target views better than the traditional image-to-image translation method which considers only the visual appearance of the scene. Extensive qualitative and quantitative evaluations support the effectiveness of our frameworks, compared to two state of the art methods, for natural scene generation across drastically different views.
Publication Date
12-14-2018
Publication Title
Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Number of Pages
3501-3510
Document Type
Article; Proceedings Paper
Personal Identifier
scopus
DOI Link
https://doi.org/10.1109/CVPR.2018.00369
Copyright Status
Unknown
Socpus ID
85061808022 (Scopus)
Source API URL
https://api.elsevier.com/content/abstract/scopus_id/85061808022
STARS Citation
Regmi, Krishna and Borji, Ali, "Cross-View Image Synthesis Using Conditional Gans" (2018). Scopus Export 2015-2019. 10044.
https://stars.library.ucf.edu/scopus2015/10044