Research
ORSIFlow: Saliency-Guided Rectified Flow for Optical Remote Sensing Salient Object Detection
arXiv:2603.28584v2 Announce Type: replace Abstract: Optical Remote Sensing Image Salient Object Detection (ORSI-SOD) remains challenging due to complex backgrounds, low contrast, irregular object shap
arXiv:2603.28584v2 Announce Type: replace Abstract: Optical Remote Sensing Image Salient Object Detection (ORSI-SOD) remains challenging due to complex backgrounds, low contrast, irregular object shapes, and large variations in object scale. Existing discriminative methods directly regress saliency maps, while recent diffusion-based generative approaches suffer from stochastic sampling and high computational cost. In this paper, we propose ORSIFlow, a saliency-guided rectified flow framework that reformulates ORSI-SOD as a deterministic latent flow generation problem. ORSIFlow performs saliency mask generation in a compact latent space constructed by a frozen variational autoencoder, enabling efficient inference with only a few steps. To enhance saliency awareness, we design a Salient Feature Discriminator for global semantic discrimination and a Salient Feature Calibrator for precise boundary refinement. Extensive experiments on multiple public benchmarks show that ORSIFlow achieves state-of-the-art performance with significantly improved efficiency.
Related
- DGSSM: Diffusion guided state-space models for multimodal salient object detection
- DiffuSAM: Diffusion Guided Zero-Shot Object Grounding for Remote Sensing Imagery
- ChangeBridge: Spatiotemporal Image Generation with Multimodal Controls for Remote Sensing
- FSDETR: Frequency-Spatial Feature Enhancement for Small Object Detection
Source: arXiv cs.CV | 2026-04-21