Spatial-Temporal Super-Resolution of Satellite Imagery via Conditional Pixel SynthesisDownload PDF

21 May 2021, 20:44 (edited 23 Dec 2021)NeurIPS 2021 PosterReaders: Everyone
  • Keywords: Remote Sensing, Super-Resolution, Generative Models
  • TL;DR: A conditional pixel synthesis model that uses the fine-grained spatial information in HR images and the abundant temporal availability of LR images to create the desired synthetic HR images of the target location and time.
  • Abstract: High-resolution satellite imagery has proven useful for a broad range of tasks, including measurement of global human population, local economic livelihoods, and biodiversity, among many others. Unfortunately, high-resolution imagery is both infrequently collected and expensive to purchase, making it hard to efficiently and effectively scale these downstream tasks over both time and space. We propose a new conditional pixel synthesis model that uses abundant, low-cost, low-resolution imagery to generate accurate high-resolution imagery at locations and times in which it is unavailable. We show that our model attains photo-realistic sample quality and outperforms competing baselines on a key downstream task – object counting – particularly in geographic locations where conditions on the ground are changing rapidly.
  • Supplementary Material: pdf
  • Code Of Conduct: I certify that all co-authors of this work have read and commit to adhering to the NeurIPS Statement on Ethics, Fairness, Inclusivity, and Code of Conduct.
  • Code: https://github.com/KellyYutongHe/satellite-pixel-synthesis-pytorch
9 Replies

Loading