DiffuSAM: Diffusion Guided Zero-Shot Object Grounding for Remote Sensing Imagery
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866918456834654208 |
|---|---|
| author | Sethi, Geet Shah, Panav Gandhe, Ashutosh Nayak, Soumitra Darshan |
| author_facet | Sethi, Geet Shah, Panav Gandhe, Ashutosh Nayak, Soumitra Darshan |
| contents | Diffusion models have emerged as powerful tools for a wide range of vision tasks, including text-guided image generation and editing. In this work, we explore their potential for object grounding in remote sensing imagery. We propose a hybrid pipeline that integrates diffusion-based localization cues with state-of-the-art segmentation models such as RemoteSAM and SAM3 to obtain more accurate bounding boxes. By leveraging the complementary strengths of generative diffusion models and foundational segmentation models, our approach enables robust and adaptive object localization across complex scenes. Experiments demonstrate that our pipeline significantly improves localization performance, achieving over a 14% increase in Acc@0.5 compared to existing state-of-the-art methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_18201 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | DiffuSAM: Diffusion Guided Zero-Shot Object Grounding for Remote Sensing Imagery Sethi, Geet Shah, Panav Gandhe, Ashutosh Nayak, Soumitra Darshan Computer Vision and Pattern Recognition Machine Learning Diffusion models have emerged as powerful tools for a wide range of vision tasks, including text-guided image generation and editing. In this work, we explore their potential for object grounding in remote sensing imagery. We propose a hybrid pipeline that integrates diffusion-based localization cues with state-of-the-art segmentation models such as RemoteSAM and SAM3 to obtain more accurate bounding boxes. By leveraging the complementary strengths of generative diffusion models and foundational segmentation models, our approach enables robust and adaptive object localization across complex scenes. Experiments demonstrate that our pipeline significantly improves localization performance, achieving over a 14% increase in Acc@0.5 compared to existing state-of-the-art methods. |
| title | DiffuSAM: Diffusion Guided Zero-Shot Object Grounding for Remote Sensing Imagery |
| topic | Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2604.18201 |