Search papers, labs, and topics across Lattice.
This paper introduces PC-SAM, a novel framework integrating automatic road segmentation with interactive refinement for high-resolution remote sensing images. It addresses the limitations of existing fully automatic methods and the poor performance of the original SAM model in fine-grained road segmentation. By employing a patch-constrained fine-tuning strategy, PC-SAM restricts the influence of point prompts to corresponding image patches, enabling precise local mask refinement.
SAM's impressive interactive segmentation skills don't translate to remote sensing road extraction until you constrain point prompts to local patches, unlocking fine-grained control.
Road masks obtained from remote sensing images effectively support a wide range of downstream tasks. In recent years, most studies have focused on improving the performance of fully automatic segmentation models for this task, achieving significant gains. However, current fully automatic methods are still insufficient for identifying certain challenging road segments and often produce false positive and false negative regions. Moreover, fully automatic segmentation does not support local segmentation of regions of interest or refinement of existing masks. Although the SAM model is widely used as an interactive segmentation model and performs well on natural images, it shows poor performance in remote sensing road segmentation and cannot support fine-grained local refinement. To address these limitations, we propose PC-SAM, which integrates fully automatic road segmentation and interactive segmentation within a unified framework. By carefully designing a fine-tuning strategy, the influence of point prompts is constrained to their corresponding patches, overcoming the inability of the original SAM to perform fine local corrections and enabling fine-grained interactive mask refinement. Extensive experiments on several representative remote sensing road segmentation datasets demonstrate that, when combined with point prompts, PC-SAM significantly outperforms state-of-the-art fully automatic models in road mask segmentation, while also providing flexible local mask refinement and local road segmentation. The code will be available at https://github.com/Cyber-CCOrange/PC-SAM.
