Breaking the Box: Enhancing Remote Sensing Image Segmentation with Freehand Sketches
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866917958506250240 |
|---|---|
| author | Zang, Ying Gao, Yuncan Zhang, Jiangi Hu, Yuangi Cao, Runlong Zhu, Lanyun Zhu, Qi Ji, Deyi Xu, Renjun Chen, Tianrun |
| author_facet | Zang, Ying Gao, Yuncan Zhang, Jiangi Hu, Yuangi Cao, Runlong Zhu, Lanyun Zhu, Qi Ji, Deyi Xu, Renjun Chen, Tianrun |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_12191 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Breaking the Box: Enhancing Remote Sensing Image Segmentation with Freehand Sketches Zang, Ying Gao, Yuncan Zhang, Jiangi Hu, Yuangi Cao, Runlong Zhu, Lanyun Zhu, Qi Ji, Deyi Xu, Renjun Chen, Tianrun Computer Vision and Pattern Recognition 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. |
| title | Breaking the Box: Enhancing Remote Sensing Image Segmentation with Freehand Sketches |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2503.12191 |