{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/uncrtaints-uncertainty-quantification-for","title":"UnCRtainTS: Uncertainty Quantification for Cloud Removal in Optical Satellite Time Series","arxiv_id":"2304.05464","date":"2023-04-11","proceeding":null,"authors":["Patrick Ebel","Vivien Sainte Fare Garnot","Michael Schmitt","Jan Dirk Wegner","Xiao Xiang Zhu"],"abstract":"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.","url_abs":"https://arxiv.org/abs/2304.05464v1","url_pdf":"https://arxiv.org/pdf/2304.05464v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"uncrtaints-uncertainty-quantification-for","repo_url":"https://github.com/PatrickTUM/UnCRtainTS","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"cloud-removal","task_name":"Cloud Removal"},{"task_slug":"image-reconstruction","task_name":"Image Reconstruction"},{"task_slug":"time-series-1","task_name":"Time Series"},{"task_slug":"uncertainty-quantification","task_name":"Uncertainty Quantification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/cloud-removal-on-sen12ms-cr","task":"Cloud Removal","dataset":"SEN12MS-CR","model":"UnCRtainTS L2","rank_in_archive_order":3,"of":10,"metrics":{"MAE":"0.027","PSNR":"28.90","SAM":"8.320","SSIM":"0.880"},"uses_additional_data":false},{"leaderboard":"/sota/cloud-removal-on-sen12ms-cr-ts","task":"Cloud Removal","dataset":"SEN12MS-CR-TS","model":"UnCRtainTS L2","rank_in_archive_order":2,"of":7,"metrics":{"PSNR":"27.23","RMSE":"0.049","SAM":"10.168","SSIM":"0.859"},"uses_additional_data":false},{"leaderboard":"/sota/cloud-removal-on-sen12ms-cr-ts","task":"Cloud Removal","dataset":"SEN12MS-CR-TS","model":"UnCRtainTS σ","rank_in_archive_order":3,"of":7,"metrics":{"PSNR":"27.84","RMSE":"0.051","SAM":"10.160","SSIM":"0.866"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2304.05464","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}