AllClear: A Comprehensive Dataset and Benchmark for Cloud Removal in Satellite Imagery

Hangyu Zhou, Chia Hsiang Kao, Cheng Perng Phoo, Utkarsh Mall, Bharath Hariharan, Kavita Bala

Keywords: remote sensing, cloud removal, satellite imagery

TL;DR: We propose a large-scale, multi-modality, and multi-temporal dataset and benchmark for cloud removal in satellite imagery with 23,742 regions-of-interest and four million images.

Abstract:

Clouds in satellite imagery pose a significant challenge for downstream applications.
A major challenge in current cloud removal research is the absence of a comprehensive benchmark and a sufficiently large and diverse training dataset.
To address this problem, we introduce the largest public dataset -- *AllClear* for cloud removal, featuring 23,742 globally distributed regions of interest (ROIs) with diverse land-use patterns, comprising 4 million images in total. Each ROI includes complete temporal captures from the year 2022, with (1) multi-spectral optical imagery from Sentinel-2 and Landsat 8/9, (2) synthetic aperture radar (SAR) imagery from Sentinel-1, and (3) auxiliary remote sensing products such as cloud masks and land cover maps.
We validate the effectiveness of our dataset by benchmarking performance, demonstrating the scaling law - the PSNR rises from $28.47$ to $33.87$ with $30\times$ more data, and conducting ablation studies on the temporal length and the importance of individual modalities. This dataset aims to provide comprehensive coverage of the Earth's surface and promote better cloud removal results.

Submission Number: 1200