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.
@article{arxiv.2503.12191,
title = {Breaking the Box: Enhancing Remote Sensing Image Segmentation with Freehand Sketches},
author = {Ying Zang and Yuncan Gao and Jiangi Zhang and Yuangi Hu and Runlong Cao and Lanyun Zhu and Qi Zhu and Deyi Ji and Renjun Xu and Tianrun Chen},
journal= {arXiv preprint arXiv:2503.12191},
year = {2025}
}