Spatial-Temporal Super-Resolution of Satellite Imagery via Conditional Pixel Synthesis

TL;DR

This paper introduces a conditional pixel synthesis model that enhances low-resolution satellite images to high-resolution, improving accuracy in tasks like object counting, especially in dynamic geographic regions.

Contribution

The paper presents a novel conditional pixel synthesis approach for super-resolution of satellite imagery, outperforming existing methods in accuracy and realism.

Findings

Achieves photo-realistic high-resolution images from low-resolution inputs.

Outperforms baseline models in object counting accuracy.

Effective in rapidly changing geographic conditions.

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.