Tag
The paper proposes Geo-Anchored Cloud Removal (GACR), a framework that uses Observation-Anchored Residual Flow and Geo-Contextual Prior Alignment to remove clouds from optical remote sensing images while preserving semantic structures for downstream tasks.
DRIFT is a framework that adapts pretrained vision-language models for continuous output decoding by combining coarse prediction with iterative flow matching refinement, improving performance on perception and planning tasks.