| --- |
| license: mit |
| tags: |
| - kornia |
| - feature-matching |
| --- |
| |
| # kornia/loftr |
|
|
| Pretrained weights for **LoFTR** (Detector-Free Local Feature Matching with Transformers), |
| used by [`kornia.feature.LoFTR`](https://kornia.readthedocs.io/en/latest/feature.html). |
|
|
| LoFTR builds dense coarse-to-fine correspondences directly from feature maps using |
| linear attention, without any keypoint detection step. Trained on outdoor (MegaDepth) |
| and indoor (ScanNet) datasets. CVPR 2021. |
|
|
| **Original repo:** [zju3dv/LoFTR](https://github.com/zju3dv/LoFTR) |
|
|
| ## Weights |
|
|
| | File | Scene type | |
| |------|-----------| |
| | `loftr_outdoor.ckpt` | Outdoor (MegaDepth) | |
| | `loftr_indoor_ds_new.ckpt` | Indoor (ScanNet, updated) | |
| | `loftr_indoor.ckpt` | Indoor (ScanNet) | |
|
|
| ## Citation |
|
|
| ```bibtex |
| @inproceedings{LoFTR2021, |
| title = {{LoFTR}: Detector-Free Local Feature Matching with Transformers}, |
| author = {Sun, Jiaming and Shen, Zehong and Wang, Yuang |
| and Bao, Hujun and Zhou, Xiaowei}, |
| booktitle = {CVPR}, |
| year = {2021} |
| } |
| ``` |
|
|
