用手绘草图提升遥感图像分割，更直观高效。
Breaking the Box: Enhancing Remote Sensing Image Segmentation with Freehand Sketches
- 用自由手绘草图替代点/框提示，交互更自然。
- 在新数据集LTL-Sensing上显著优于SAM等模型。
- 适合需要快速标注遥感图像的科研与应用人员。
本文通过三项关键贡献推进遥感图像的零样本交互式分割。首先，提出一种新颖的草图提示方法，用户可直观勾勒目标，优于传统点或框提示。其次，构建首个将人类草图与遥感图像配对的数据集LTL-Sensing，为后续研究设立基准。第三，提出LTL-Net，其多输入提示传输模块专为自由手绘草图设计。大量实验表明，该方法在分割精度与鲁棒性上显著优于当前最优方法如SAM，促进遥感分析中更直观的人机协作，拓展应用场景。
原文摘要 · Abstract (English)
This work advances zero-shot interactive segmentation for remote sensing imagery through three key contributions. First, we propose a novel sketch-based prompting method, enabling users to intuitively outline objects, surpassing traditional point or box prompts. Second, we introduce LTL-Sensing, the first dataset pairing human sketches with remote sensing imagery, setting a benchmark for future research. Third, we present LTL-Net, a model featuring a multi-input prompting transport module tailored for freehand sketches. Extensive experiments show our approach significantly improves segmentation accuracy and robustness over state-of-the-art methods like SAM, fostering more intuitive human-AI collaboration in remote sensing analysis and enhancing its applications.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。