March 18, 2024, 4:46 a.m. | Mikolaj Czerkawski, Christos Tachtatzis

cs.CV updates on arXiv.org arxiv.org

arXiv:2311.03008v2 Announce Type: replace
Abstract: The letter investigates the utility of text-to-image inpainting models for satellite image data. Two technical challenges of injecting structural guiding signals into the generative process as well as translating the inpainted RGB pixels to a wider set of MSI bands are addressed by introducing a novel inpainting framework based on StableDiffusion and ControlNet as well as a novel method for RGB-to-MSI translation. The results on a wider set of data suggest that the inpainting synthesized …

abstract arxiv capability challenges cs.cv data diffusion diffusion models edge generative guidance image image data image diffusion inpainting pixels process satellite set technical text text-to-image type utility

AI Research Scientist

@ Vara | Berlin, Germany and Remote

Data Architect

@ University of Texas at Austin | Austin, TX

Data ETL Engineer

@ University of Texas at Austin | Austin, TX

Lead GNSS Data Scientist

@ Lurra Systems | Melbourne

Senior Machine Learning Engineer (MLOps)

@ Promaton | Remote, Europe

AI Engineering Manager

@ M47 Labs | Barcelona, Catalunya [Cataluña], Spain