Generating Ground-Level Images From Overhead Imagery Using GANs with Yi Zhu

Today we're joined by Yi Zhu, a PhD candidate at UC Merced focused on geospatial image analysis. In our conversation, Yi and I discuss his recent paper "What Is It Like Down There? Generating Dense Ground-Level Views and Image Features From Overhead Imagery Using Conditional Generative Adversarial Networks." Yi and I discuss the goal of this research, which is to train effective land-use classifiers on proximate, or ground-level, images, and how he uses conditional GANs along with images sourced from social media to generate artificial ground-level images for this task. We also explore future research directions such as the use of reversible generative networks as proposed in the recently released OpenAI Glow paper to producing higher resolution images.