Convolutional Neural Processes for Inpainting Satellite Images

TL;DR

This paper introduces a novel inpainting method for satellite images using convolutional neural processes, effectively handling missing data by modeling each image as a task, outperforming classical and existing deep learning approaches.

Contribution

It proposes a meta-learning approach with ConvNPs for satellite image inpainting, explicitly leveraging spatiotemporal structure and demonstrating superior performance.

Findings

ConvNPs outperform classical inpainting methods.

ConvNPs outperform state-of-the-art deep learning models.

Effective on in-distribution and out-of-distribution images.

Abstract

The widespread availability of satellite images has allowed researchers to model complex systems such as disease dynamics. However, many satellite images have missing values due to measurement defects, which render them unusable without data imputation. For example, the scanline corrector for the LANDSAT 7 satellite broke down in 2003, resulting in a loss of around 20\% of its data. Inpainting involves predicting what is missing based on the known pixels and is an old problem in image processing, classically based on PDEs or interpolation methods, but recent deep learning approaches have shown promise. However, many of these methods do not explicitly take into account the inherent spatiotemporal structure of satellite images. In this work, we cast satellite image inpainting as a natural meta-learning problem, and propose using convolutional neural processes (ConvNPs) where we frame each satellite image as its own task or 2D regression problem. We show ConvNPs can outperform classical methods and state-of-the-art deep learning inpainting models on a scanline inpainting problem for LANDSAT 7 satellite images, assessed on a variety of in and out-of-distribution images.