Papers › UnCRtainTS: Uncertainty Quantification for Cloud Removal in Optical Satellite Time Series

UnCRtainTS: Uncertainty Quantification for Cloud Removal in Optical Satellite Time Series

11 Apr 2023arXiv:2304.05464archive 2025-07-28

Patrick Ebel, Vivien Sainte Fare Garnot, Michael Schmitt, Jan Dirk Wegner, Xiao Xiang Zhu

Clouds and haze often occlude optical satellite images, hindering continuous, dense monitoring of the Earth's surface. Although modern deep learning methods can implicitly learn to ignore such occlusions, explicit cloud removal as pre-processing enables manual interpretation and allows training models when only few annotations are available. Cloud removal is challenging due to the wide range of occlusion scenarios -- from scenes partially visible through haze, to completely opaque cloud coverage. Furthermore, integrating reconstructed images in downstream applications would greatly benefit from trustworthy quality assessment. In this paper, we introduce UnCRtainTS, a method for multi-temporal cloud removal combining a novel attention-based architecture, and a formulation for multivariate uncertainty prediction. These two components combined set a new state-of-the-art performance in terms of image reconstruction on two public cloud removal datasets. Additionally, we show how the well-calibrated predicted uncertainties enable a precise control of the reconstruction quality.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

PatrickTUM/UnCRtainTS mentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Cloud RemovalImage ReconstructionTime SeriesUncertainty Quantification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Cloud Removal SEN12MS-CR UnCRtainTS L2 MAE 0.027 #3 of 10 Archive leaderboard report
Cloud Removal SEN12MS-CR UnCRtainTS L2 PSNR 28.90 #3 of 10 Archive leaderboard report
Cloud Removal SEN12MS-CR UnCRtainTS L2 SAM 8.320 #3 of 10 Archive leaderboard report
Cloud Removal SEN12MS-CR UnCRtainTS L2 SSIM 0.880 #3 of 10 Archive leaderboard report
Cloud Removal SEN12MS-CR-TS UnCRtainTS L2 PSNR 27.23 #2 of 7 Archive leaderboard report
Cloud Removal SEN12MS-CR-TS UnCRtainTS L2 RMSE 0.049 #2 of 7 Archive leaderboard report
Cloud Removal SEN12MS-CR-TS UnCRtainTS L2 SAM 10.168 #2 of 7 Archive leaderboard report
Cloud Removal SEN12MS-CR-TS UnCRtainTS L2 SSIM 0.859 #2 of 7 Archive leaderboard report
Cloud Removal SEN12MS-CR-TS UnCRtainTS σ PSNR 27.84 #3 of 7 Archive leaderboard report
Cloud Removal SEN12MS-CR-TS UnCRtainTS σ RMSE 0.051 #3 of 7 Archive leaderboard report
Cloud Removal SEN12MS-CR-TS UnCRtainTS σ SAM 10.160 #3 of 7 Archive leaderboard report
Cloud Removal SEN12MS-CR-TS UnCRtainTS σ SSIM 0.866 #3 of 7 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections