---
license: apache-2.0
tags:
- image-matching
- computer-vision
- feature-matching
library_name: image-matching-models
---

# TopicFM Plus

Plus variant of TopicFM with 8-head attention and linear attention mechanism.

## Usage

```python
from matching import get_matcher

matcher = get_matcher("topicfm-plus", device="cuda")
mkpts0, mkpts1, _, _, _, _ = matcher(img0, img1)
```

## Links
- [TopicFM](https://huggingface.co/image-matching-models/topicfm)
- [Original repository](https://github.com/TruongKhang/TopicFM)
- [Image Matching Models](https://github.com/gmberton/image-matching-models)