Formatting the Landscape: Spatial conditional GAN for varying population in satellite imagery

December 08, 2020 · Entered Twilight · 🏛 arXiv.org

"Last commit was 5.0 years ago (≥5 year threshold)"

Evidence collected by the PWNC Scanner

Repo contents: .gitignore, Population Painter Colab.ipynb, Population Painter.ipynb, README.md, README_ALAE.md, SCALAE_paper_figures, SCALAE_population_paper_figures.ipynb, SCALAE_reconstruction_paper_figures.ipynb, align_faces.py, checkpointer.py, configs, custom_adam.py, dataloader.py, dataset_preparation, defaults.py, interactive_demo.py, launcher.py, lod_driver.py, losses.py, lreq.py, make_figures, metrics, model.py, model_separate.py, net.py, principal_directions, registry.py, requirements.txt, scheduler.py, style_mixing, tracker.py, train_alae.py, train_alae_separate.py, train_scalae.py, training_artifacts, utils.py

Authors Tomas Langer, Natalia Fedorova, Ron Hagensieker arXiv ID 2101.05069 Category cs.CV: Computer Vision Cross-listed cs.LG, eess.IV Citations 3 Venue arXiv.org Repository https://github.com/LendelTheGreat/SCALAE/ ⭐ 13 Last Checked 1 month ago

Abstract

Climate change is expected to reshuffle the settlement landscape: forcing people in affected areas to migrate, to change their lifeways, and continuing to affect demographic change throughout the world. Changes to the geographic distribution of population will have dramatic impacts on land use and land cover and thus constitute one of the major challenges of planning for climate change scenarios. In this paper, we explore a generative model framework for generating satellite imagery conditional on gridded population distributions. We make additions to the existing ALAE architecture, creating a spatially conditional version: SCALAE. This method allows us to explicitly disentangle population from the model's latent space and thus input custom population forecasts into the generated imagery. We postulate that such imagery could then be directly used for land cover and land use change estimation using existing frameworks, as well as for realistic visualisation of expected local change. We evaluate the model by comparing pixel and semantic reconstructions, as well as calculate the standard FID metric. The results suggest the model captures population distributions accurately and delivers a controllable method to generate realistic satellite imagery.