{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/void-filling-of-digital-elevation-models-with","title":"Void Filling of Digital Elevation Models with Deep Generative Models","arxiv_id":"1811.12693","date":"2018-11-30","proceeding":null,"authors":["Konstantinos Gavriil","Georg Muntingh","Oliver J. D. Barrowclough"],"abstract":"In recent years, advances in machine learning algorithms, cheap computational\nresources, and the availability of big data have spurred the deep learning\nrevolution in various application domains. In particular, supervised learning\ntechniques in image analysis have led to superhuman performance in various\ntasks, such as classification, localization, and segmentation, while\nunsupervised learning techniques based on increasingly advanced generative\nmodels have been applied to generate high-resolution synthetic images\nindistinguishable from real images.\n  In this paper we consider a state-of-the-art machine learning model for image\ninpainting, namely a Wasserstein Generative Adversarial Network based on a\nfully convolutional architecture with a contextual attention mechanism. We show\nthat this model can successfully be transferred to the setting of digital\nelevation models (DEMs) for the purpose of generating semantically plausible\ndata for filling voids. Training, testing and experimentation is done on\nGeoTIFF data from various regions in Norway, made openly available by the\nNorwegian Mapping Authority.","url_abs":"http://arxiv.org/abs/1811.12693v2","url_pdf":"http://arxiv.org/pdf/1811.12693v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"void-filling-of-digital-elevation-models-with","repo_url":"https://github.com/konstantg/dem-fill","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"machine-learning","task_name":"BIG-bench Machine Learning"},{"task_slug":null,"task_name":"Generative Adversarial Network"},{"task_slug":"image-inpainting","task_name":"Image Inpainting"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1811.12693","atlas_url":"https://app.syntology.ai/?focus=1811.12693","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}