Remove usage section

README.md

@@ -47,36 +47,6 @@ language:
 
 When camera intrinsics are not available (e.g., in-the-wild images), the model can predict intrinsics internally. When sparse or dense depth (e.g., from LiDAR) is provided, it is fused for improved 3D localization.
 
-## Usage
-
-```python
-from wilddet3d import build_model, preprocess
-import numpy as np
-from PIL import Image
-
-# Build model (auto-downloads checkpoint from this repo)
-model = build_model(
-    checkpoint="allenai/WildDet3D",
-    score_threshold=0.3,
-    skip_pretrained=True,
-)
-
-# Load and preprocess image
-image = np.array(Image.open("image.jpg")).astype(np.float32)
-data = preprocess(image, intrinsics=None)
-
-# Text prompt
-results = model(
-    images=data["images"].cuda(),
-    intrinsics=data["intrinsics"].cuda()[None],
-    input_hw=[data["input_hw"]],
-    original_hw=[data["original_hw"]],
-    padding=[data["padding"]],
-    input_texts=["car", "person", "bicycle"],
-)
-boxes, boxes3d, scores, scores_2d, scores_3d, class_ids, depth_maps = results
-```
-
 ## Citation
 
 ```bibtex