| --- |
| license: mit |
| library_name: libreyolo |
| pipeline_tag: image-segmentation |
| tags: |
| - background-removal |
| - matte |
| - dichotomous-image-segmentation |
| - ben2 |
| - libreyolo |
| --- |
| |
| # LibreBEN2b-matte |
|
|
| BEN2 Base background removal, repackaged for LibreYOLO's `matte` task. It |
| predicts a soft alpha matte at a fixed native 1024x1024 resolution. |
|
|
| ```python |
| from libreyolo import LibreYOLO |
| |
| model = LibreYOLO("LibreBEN2b-matte.pt") |
| result = model.predict("product.jpg") |
| result[0].matte.array # (H, W) float alpha in [0, 1] |
| result[0].save("cut.png") # transparent-background PNG |
| ``` |
|
|
| ## Source |
|
|
| Derived from [PramaLLC/BEN2](https://github.com/PramaLLC/BEN2) at commit |
| `2c99a5da477b5523585bfa5c893888a6e818a8f6`, using the released checkpoint from |
| [PramaLLC/BEN2](https://huggingface.co/PramaLLC/BEN2) at revision |
| `e48a20765fb421d19dcdb0bf3cc61e802ca5ec8f`. |
| Copyright (c) 2025 Prama LLC. Licensed under the MIT License. |
|
|
| Training data provenance (upstream): DIS5K and Prama LLC's proprietary 22K |
| segmentation dataset. This repository redistributes only the released MIT |
| checkpoint and does not redistribute training data. |
|
|
| ## Modifications |
|
|
| State-dict metadata wrap only. Learned parameters are unchanged. The native |
| LibreYOLO fp32 forward matches the released BEN2 Base network with |
| `max_abs_diff == 0` for batch sizes 1 and 2. See |
| `weights/convert_ben2_weights.py` in the |
| [LibreYOLO source repository](https://github.com/LibreYOLO/libreyolo). |
|
|
| The port returns raw logits for LibreYOLO's shared matte postprocessing and |
| does not include BEN2's optional media or foreground-refinement helpers. |
|
|
| ## License |
|
|
| MIT License. See the [`LICENSE`](./LICENSE) and [`NOTICE`](./NOTICE) files. |
|
|
