Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2605.27726 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910264012570624 |
|---|---|
| author | Fallah, Forouzan Hsu, Chia Yu Li, Wenwen Liljedahl, Anna Yang, Yezhou |
| author_facet | Fallah, Forouzan Hsu, Chia Yu Li, Wenwen Liljedahl, Anna Yang, Yezhou |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_27726 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Asynchronous Remote Sensing Time-Series Fusion for Cloud Removal and Anytime Reconstruction Fallah, Forouzan Hsu, Chia Yu Li, Wenwen Liljedahl, Anna Yang, Yezhou Computer Vision and Pattern Recognition 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. |
| title | Asynchronous Remote Sensing Time-Series Fusion for Cloud Removal and Anytime Reconstruction |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2605.27726 |