Update README.md

README.md

@@ -20,11 +20,10 @@ 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
-point backbone. A single forward pass over an RGB point cloud produces a fixed set of
+convnet transformer 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). The vocabulary is chosen at inference time — it is not baked into the
-weights — so the model can be queried with any label set.
+prompt ensembling).
 
 Project page: https://nvlabs.github.io/SpaCeFormer/
 
@@ -46,17 +45,17 @@ 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 | mAP50 | recall (class-agnostic) |
+| Benchmark | mAP |
 |---|---:|---:|---:|
-| ScanNet200 | **0.1265** | 0.210 | 0.756 |
-| ScanNet++ | 0.2217 | — | — |
-| Replica | 0.2644 | — | — |
+| ScanNet200 | **0.1265** |
+| 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 labeling + mask post-processing live in the
+It returns **raw** predictions; open-vocab CLIP feature + mask post-processing live in the
 demo repo / HuggingFace Space, not in WarpConvNet.
 
 ```python
@@ -86,7 +85,7 @@ 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/evaluated on indoor scenes (ScanNet200 / ScanNet++ / Replica);
+- **Domain:** trained on indoor scenes (ScanNet200 / ScanNet++ / ARKit);
   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.