Views
No views yet
config.json, pipeline, and weights.SegEarth-OV/
├── OV/ # CLIP (OpenAI ViT-B/16) + SimFeatUp
│ ├── config.json
│ ├── pipeline.py
│ ├── upsamplers.py
│ ├── prompts/
│ ├── configs/cls_*.txt
│ ├── weights/featup/ # SimFeatUp checkpoints
│ └── weights/backbone/ # OpenAI CLIP (clip-vit-base-patch16)
├── OV-2/ # AlignEarth (SAR) + SimFeatUp
│ ├── config.json
│ ├── pipeline.py
│ ├── weights/featup/
│ └── weights/backbone/ # AlignEarth-SAR-ViT-B-16
├── OV-3/ # SAM3 (no featup)
│ ├── config.json
│ ├── pipeline.py
│ ├── configs/
│ └── weights/backbone/ # facebook/sam3 (sam3.pt)
└── model_config.json| Variant | Backbone | Location |
|---|---|---|
| OV | OpenAI CLIP ViT-B/16 | OV/weights/backbone/clip-vit-base-patch16/ |
| OV-2 | AlignEarth-SAR-ViT-B-16 | OV-2/weights/backbone/AlignEarth-SAR-ViT-B-16/ |
| OV-3 | SAM3 | OV-3/weights/backbone/sam3/sam3.pt |
| OV, OV-2 | SimFeatUp (jbu_one, etc.) | OV/weights/featup/, OV-2/weights/featup/ |
1# OV-2 with AlignEarth (SAR)
2from pipeline import SegEarthPipeline
3pipe = SegEarthPipeline() # loads OV-2/config.json
4seg = pipe(image)
5
6# Or: cd OV-2 && python -c "from pipeline import load; pipe = load()"1from pipeline import SegEarthPipeline
2
3pipe = SegEarthPipeline(variant="OV-2")
4pipe = SegEarthPipeline(variant="OV")
5pipe = SegEarthPipeline(variant="OV-3") # requires sam3 packagepipe = SegEarthPipeline(variant="OV-2", class_names_path="OV-2/configs/cls_yeseg_sar.txt")| Subfolder | Backbone | Model ID | FeatUp |
|---|---|---|---|
| OV | CLIP | openai/clip-vit-base-patch16 | jbu_one |
| OV-2 | AlignEarth | BiliSakura/AlignEarth-SAR-ViT-B-16 | jbu_one |
| OV-3 | SAM3 | facebook/sam3 | None |
1@InProceedings{Li_2025_CVPR,
2 author = {Li, Kaiyu and Liu, Ruixun and Cao, Xiangyong and Bai, Xueru and Zhou, Feng and Meng, Deyu and Wang, Zhi},
3 title = {SegEarth-OV: Towards Training-Free Open-Vocabulary Segmentation for Remote Sensing Images},
4 booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
5 year = {2025},
6 pages = {10545--10556}
7}
8
9@article{li2025segearthov2,
10 title = {Annotation-Free Open-Vocabulary Segmentation for Remote-Sensing Images},
11 author = {Li, Kaiyu and Cao, Xiangyong and Liu, Ruixun and Wang, Shihong and Jiang, Zixuan and Wang, Zhi and Meng, Deyu},
12 journal = {arXiv preprint arXiv:2508.18067},
13 year = {2025}
14}
15
16@article{li2025segearthov3,
17 title = {SegEarth-OV3: Exploring SAM 3 for Open-Vocabulary Semantic Segmentation in Remote Sensing Images},
18 author = {Li, Kaiyu and Zhang, Shengqi and Deng, Yupeng and Wang, Zhi and Meng, Deyu and Cao, Xiangyong},
19 journal = {arXiv preprint arXiv:2512.08730},
20 year = {2025}
21}