Jinjiang Li

Physics-Aware Feature Calibration Network for Remote Sensing Image Segmentation

In remote sensing image segmentation, regions with sharp intensity variations caused by complex illumination and ground objects significantly constrain segmentation accuracy. Most existing methods attempt to enhance the model’s perception of these regions by introducing frequency features or relying on spatial convolut...

Underwater multi-sensor information fusion for salient object detection

This paper introduces a novel underwater salient object detection framework based on an information cross-fusion network that achieves superior performance compared to state-of-the-art approaches, highlighting its efficacy in multimodal feature integration and salient object detection.

From unstable conditioning to disentangled prompts: Variance-stable diffusion model for harsh underwater image enhancement