License: weights are CC-BY-NC-4.0 (non-commercial); add dataset usage notice; Replica is eval-only

README.md

@@ -1,5 +1,5 @@
 ---
-license: apache-2.0
+license: cc-by-nc-4.0
 library_name: warpconvnet
 pipeline_tag: image-segmentation
 tags:
@@ -20,10 +20,11 @@ tags:
 **SpaceFormer** performs **proposal-free, open-vocabulary 3D instance segmentation**.
 A Mask2Former-style query decoder (learned queries + rotary position embeddings) runs
 on top of the WarpConvNet [`SpaCeFormer`](https://github.com/NVlabs/WarpConvNet) sparse
-convnet transformer backbone. A single forward pass over an RGB point cloud produces a fixed set of
+point backbone. A single forward pass over an RGB point cloud produces a fixed set of
 query masks plus a per-query CLIP feature; each mask is labeled by comparing its CLIP
 feature against text embeddings of **arbitrary class names** (SigLIP2 text encoder, with
-prompt ensembling).
+prompt ensembling). The vocabulary is chosen at inference time — it is not baked into the
+weights — so the model can be queried with any label set.
 
 Project page: https://nvlabs.github.io/SpaCeFormer/
 
@@ -45,17 +46,17 @@ Project page: https://nvlabs.github.io/SpaCeFormer/
 Test-set mAP with the released recipe (**prompt ensembling on, TTA off, default
 proposal-free post-processing**):
 
-| Benchmark | mAP |
-|---|---:|
-| ScanNet200 | **0.1265** |
-| ScanNet++ | 0.2217 |
-| Replica | 0.2644 |
+| Benchmark | mAP | mAP50 | recall (class-agnostic) |
+|---|---:|---:|---:|
+| ScanNet200 | **0.1265** | 0.210 | 0.756 |
+| ScanNet++ | 0.2217 | — | — |
+| Replica | 0.2644 | — | — |
 
 ## How to use
 
 The model lives in WarpConvNet as `warpconvnet.models.spaceformer` (the backbone needs
 WarpConvNet's compiled CUDA extension — install a pre-built wheel or build from source).
-It returns **raw** predictions; open-vocab CLIP feature + mask post-processing live in the
+It returns **raw** predictions; open-vocab labeling + mask post-processing live in the
 demo repo / HuggingFace Space, not in WarpConvNet.
 
 ```python
@@ -85,8 +86,9 @@ e.g. its `inference.py` CLI or the Gradio `app.py`.
   point clouds (ScanNet-like) against custom class vocabularies.
 - **Open-vocab mAP is semantics-bottlenecked:** rare/fine-grained classes are weaker than
   head classes; class-agnostic mask recall is higher than the open-vocab mAP.
-- **Domain:** trained on indoor scenes (ScanNet200 / ScanNet++ / ARKit);
-  outdoor or very different sensor domains are out of distribution.
+- **Domain:** trained on indoor scenes (ScanNet, ScanNet++, ARKitScenes, Matterport3D)
+  and evaluated on ScanNet200 / ScanNet++ / Replica (Replica zero-shot); outdoor or very
+  different sensor domains are out of distribution.
 - **Large scenes:** very large clouds can exceed memory in the eval forward; the
   inference code skips such a scene (single-process) rather than crashing.
 
@@ -97,6 +99,26 @@ e.g. its `inference.py` CLI or the Gradio `app.py`.
   `load_spaceformer_checkpoint` (strips the `net.` prefix, `strict=False`).
 - `spaceformer_512_siglip2_ssccc.ckpt.provenance.json` — architecture, eval numbers, md5.
 
-## License
+## License & usage
 
-Apache-2.0.
+**These weights are released for non-commercial research use only, under
+[CC-BY-NC-4.0](https://creativecommons.org/licenses/by-nc/4.0/).** They are a derivative
+of datasets governed by non-commercial research Terms of Use, so they are **not** released
+under the permissive Apache-2.0 license that covers the *code*.
+
+The model was trained on the following datasets, each of which restricts use to
+**non-commercial research/education** under its own terms — by using these weights you
+agree to comply with all of them:
+
+- **ScanNet / ScanNet200** — [ScanNet Terms of Use](http://kaldir.vc.in.tum.de/scannet/ScanNet_TOS.pdf)
+- **ScanNet++** — [ScanNet++ Terms of Use](https://kaldir.vc.in.tum.de/scannetpp/static/scannetpp-terms-of-use.pdf)
+- **ARKitScenes** — [Apple ARKitScenes license](https://github.com/apple/ARKitScenes/blob/main/LICENSE) (non-commercial)
+- **Matterport3D** — [Matterport3D Terms of Use](https://kaldir.vc.in.tum.de/matterport/MP_TOS.pdf) (non-commercial academic)
+
+Evaluation additionally used **Replica** ([Replica Research Terms](https://github.com/facebookresearch/Replica-Dataset/blob/main/LICENSE), non-commercial), zero-shot.
+
+The accompanying **code** in [WarpConvNet](https://github.com/NVlabs/WarpConvNet) is
+licensed separately under **Apache-2.0**.
+
+> Note: this is not legal advice; for commercial use, consult the individual dataset
+> licensors. Please also cite the datasets above and the SpaceFormer project.