Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,23 @@
|
|
| 1 |
-
---
|
| 2 |
-
license: apache-2.0
|
| 3 |
-
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
---
|
| 4 |
+
|
| 5 |
+
# SAMatcher
|
| 6 |
+
|
| 7 |
+
SAMatcher is a robust feature matching method that models cross-view co-visibility with Segment Anything (SAM), improving correspondence under viewpoint/illumination/texture changes.
|
| 8 |
+
|
| 9 |
+
- GitHub: https://github.com/TwSphinx54/SAMatcher
|
| 10 |
+
- Project Page: https://xupan.top/Projects/samatcher
|
| 11 |
+
|
| 12 |
+
## Quick Start
|
| 13 |
+
|
| 14 |
+
```bash
|
| 15 |
+
huggingface-cli download SSSSSphinx/SAMatcher --local-dir ./SAMatcher
|
| 16 |
+
```
|
| 17 |
+
|
| 18 |
+
Then follow the official training/evaluation scripts in the GitHub repository.
|
| 19 |
+
|
| 20 |
+
## Notes
|
| 21 |
+
|
| 22 |
+
- Recommended Python: 3.12 (if using lockfile setup)
|
| 23 |
+
- Main dependencies include PyTorch + CUDA 12.1 and flash-attn
|