ORSIFlow applies a saliency-guided rectified flow model in latent space to produce accurate saliency maps for remote sensing images with far fewer sampling steps than diffusion methods.
Conditional diffusion models for camouflaged and salient object detection,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
ORSIFlow: Saliency-Guided Rectified Flow for Optical Remote Sensing Salient Object Detection
ORSIFlow applies a saliency-guided rectified flow model in latent space to produce accurate saliency maps for remote sensing images with far fewer sampling steps than diffusion methods.