LibreMoGe2l-normal / README.md
Xuban's picture
Mirror MoGe-2 ViT-L surface-normal weights (MIT)
9b039ba verified
|
Raw
History Blame Contribute Delete
1.07 kB
---
license: mit
library_name: libreyolo
tags:
- image-to-image
- surface-normals
- moge
---
# LibreMoGe2l-normal
MoGe-2 ViT-L/14 surface-normal estimator, repackaged in LibreYOLO checkpoint format.
## Source
Derived from [Ruicheng/moge-2-vitl-normal](https://huggingface.co/Ruicheng/moge-2-vitl-normal)
at revision `b135031bae30b5ac2ae141a0e68717795ce38340`, the exact commit LibreYOLO pins.
Copyright (c) Microsoft Corporation. Licensed under the MIT License.
The DINOv2 encoder MoGe-2 builds on is separately licensed Apache-2.0 by
Meta AI.
## Modifications
State-dict key remapping only. Learned parameters are unchanged.
See `weights/convert_moge2_weights.py` in the
[LibreYOLO source repository](https://github.com/LibreYOLO/libreyolo).
## Usage
```python
from libreyolo import LibreYOLO
model = LibreYOLO("LibreMoGe2l-normal.pt")
result = model.predict("image.jpg")[0]
normals = result.normals
```
## License
MIT License. See the [`LICENSE`](./LICENSE) and [`NOTICE`](./NOTICE) files in
this repository.