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.
Multiscale and multidimen- sional weighted network for salient object detection in optical remote sensing images,
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.