Cross-view image synthesis using geometry-guided conditional GANs

Abstract

We address the problem of generating images across two drastically different views, namely ground (street) and aerial (overhead) views. Image synthesis by itself is a very challenging computer vision task and is even more so when generation is conditioned on an image in another view. Due the difference in viewpoints, there is small overlapping field of view and little common content between these two views. Here, we try to preserve the pixel information between the views so that the generated image is a realistic representation of cross view input image. For this, we propose to use homography as a guide to map the images between the views based on the common field of view to preserve the details in the input image. We then use generative adversarial networks to inpaint the missing regions in the transformed image and add realism to it. Our exhaustive evaluation and model comparison demonstrate that utilizing geometry constraints adds fine details to the generated images and can be a better approach for cross view image synthesis than purely pixel based synthesis methods.

arXiv commentUnder review as a journal paper at CVIU. arXiv admin note: substantial text overlap with arXiv:1803.03396

References in corpus (9)

• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Conditional Generative Adversarial Nets
• GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
• Generative Adversarial Text to Image Synthesis
• Improved Techniques for Training GANs
• A note on the evaluation of generative models
• Deep multi-scale video prediction beyond mean square error
• Dual Discriminator Generative Adversarial Nets
• Geometry Guided Adversarial Facial Expression Synthesis

Cited by in corpus (6)

• Cross-view geo-localization: a survey
• Multi-Channel Attention Selection GANs for Guided Image-to-Image Translation
• From Third Person to First Person: Dataset and Baselines for Synthesis and Retrieval
• Human Silhouette and Skeleton Video Synthesis through Wi-Fi signals
• Local Class-Specific and Global Image-Level Generative Adversarial Networks for Semantic-Guided Scene Generation
• What Is It Like Down There? Generating Dense Ground-Level Views and Image Features From Overhead Imagery Using Conditional Generative Adversarial Networks