{"slug": "asynchronous-remote-sensing-time-series-fusion-for-cloud-removal-and-anytime", "title": "Asynchronous Remote Sensing Time-Series Fusion for Cloud Removal and Anytime Reconstruction", "summary": "Researchers have developed AGFlow, a spatiotemporal flow-matching model that fuses asynchronous Sentinel-1 radar and Sentinel-2 optical satellite data to remove clouds and reconstruct missing time-series frames. The model enables on-demand generation of cloud-free images at both observed and user-specified timestamps, improving fully missing-frame reconstruction by 16-19% over existing methods. This advancement addresses a critical limitation in Earth surface monitoring caused by frequent cloud cover, particularly benefiting applications like dense vegetation monitoring.", "body_md": "arXiv:2605.27726v1 Announce Type: new\nAbstract: Frequent cloud cover severely limits the usability of Sentinel-2 (S2) optical time series for Earth surface monitoring. Sentinel-1 (S1) SAR provides all-weather complementary observations, but practical S1/S2 fusion remains difficult because acquisitions are irregular and asynchronous. Many existing approaches assume temporally aligned inputs (or require external nearest-date matching) and typically restore only observed timestamps, limiting reconstruction under long gaps and preventing on-demand synthesis. We propose AGFlow (Time Aligned Generative Flow Matching), a spatiotemporal flow-matching model for S1/S2 cloud removal and time-series reconstruction with three capabilities: (1) timestamp-conditioned internal alignment that fuses asynchronous S1 and cloudy S2 observations without preprocessing-based pairing; (2) spatiotemporal, context-aware denoising that models spatial structure jointly with temporal dynamics (rather than independent per-pixel time series); and (3) anytime querying, enabling generation of cloud-free S2 frames at both observed and user-specified timestamps within the monitoring window. We evaluate on the RESTORE-DiT benchmark protocol with quantitative metrics, qualitative comparisons, and component ablations. AGFlow notably improves fully missing-frame reconstruction (MAE and RMSE reduce by 16-19% over RESTORE-DiT) and provides reliable reconstructions under persistent gaps, while also yielding competitive cloud removal performance and flexible temporal querying for downstream tasks such as dense vegetation monitoring.", "url": "https://wpnews.pro/news/asynchronous-remote-sensing-time-series-fusion-for-cloud-removal-and-anytime", "canonical_source": "https://arxiv.org/abs/2605.27726", "published_at": "2026-05-28 04:00:00+00:00", "updated_at": "2026-05-28 04:28:09.687546+00:00", "lang": "en", "topics": ["computer-vision", "machine-learning", "generative-ai", "artificial-intelligence", "neural-networks"], "entities": ["Sentinel-2", "Sentinel-1", "AGFlow", "RESTORE-DiT"], "alternates": {"html": "https://wpnews.pro/news/asynchronous-remote-sensing-time-series-fusion-for-cloud-removal-and-anytime", "markdown": "https://wpnews.pro/news/asynchronous-remote-sensing-time-series-fusion-for-cloud-removal-and-anytime.md", "text": "https://wpnews.pro/news/asynchronous-remote-sensing-time-series-fusion-for-cloud-removal-and-anytime.txt", "jsonld": "https://wpnews.pro/news/asynchronous-remote-sensing-time-series-fusion-for-cloud-removal-and-anytime.jsonld"}}