# Cloud Removal in Satellite Images Using Spatiotemporal Generative Networks

arXiv: https://arxiv.org/abs/1912.06838 · HTML: https://mlsanity.com/paper/1912.06838/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Dec 2019.

## Built on by (most cited first, 8 of 8)

- [Effective Cloud Removal for Remote Sensing Images by an Improved Mean-Reverting Denoising Model with Elucidated Design Space](https://mlsanity.com/paper/2503.23717/) (2025)
- [U-TILISE: A Sequence-to-sequence Model for Cloud Removal in Optical Satellite Time Series](https://mlsanity.com/paper/2305.13277/) (2023)
- [Multi-Modal and Multi-Resolution Data Fusion for High-Resolution Cloud Removal: A Novel Baseline and Benchmark](https://mlsanity.com/paper/2301.03432/) (2023)
- [Attentive Contextual Attention for Cloud Removal](https://mlsanity.com/paper/2411.13042/) (2024)
- [A Parallel Workflow for Polar Sea-Ice Classification using Auto-labeling of Sentinel-2 Imagery](https://mlsanity.com/paper/2403.13135/) (2024)
- [Difference-Driven Gating: Adaptive Feature Fusion for U-Net Decoder](https://mlsanity.com/paper/2607.11096/) (2026)
- [Cloud Removal from Satellite Images](https://mlsanity.com/paper/2112.15483/) (2021)
- [GeoCR: Learning a Generalist Cloud Removal Prior from Heterogeneous Observations](https://mlsanity.com/paper/2609.32510/) (2026)

## Abstract (arXiv)

Satellite images hold great promise for continuous environmental monitoring and earth observation. Occlusions cast by clouds, however, can severely limit coverage, making ground information extraction more difficult. Existing pipelines typically perform cloud removal with simple temporal composites and hand-crafted filters. In contrast, we cast the problem of cloud removal as a conditional image synthesis challenge, and we propose a trainable spatiotemporal generator network (STGAN) to remove clouds. We train our model on a new large-scale spatiotemporal dataset that we construct, containing 97640 image pairs covering all continents. We demonstrate experimentally that the proposed STGAN model outperforms standard models and can generate realistic cloud-free images with high PSNR and SSIM values across a variety of atmospheric conditions, leading to improved performance in downstream tasks such as land cover classification.