refactor(compressors): migrate to centralized model loaders

- Refactor model_loader.py: improve return type annotations from tuple[Any, Any] to tuple[AutoImageProcessor, AutoModel]
- Refactor proposal/core.py: add input validation for mask array dimensionality, handle 2D masks and batch dimensions gracefully
- Refactor proposal_segament.ipynb: replace inline model loading with centralized load_owlv2_model() and load_sam_model() functions, use batched detect_objects_batch() and generate_proposals_batch() APIs

mini-nav/compressors/model_loader.py

@@ -34,7 +34,7 @@ def load_sam_model(
 
 def load_dino_model(
     model_name: str = "facebook/dinov2-large",
-) -> tuple[Any, Any]:
+) -> tuple[AutoImageProcessor, AutoModel]:
     device = get_device()
 
     processor = AutoImageProcessor.from_pretrained(model_name)

mini-nav/compressors/proposal/core.py

@@ -205,16 +205,14 @@ def _masks_to_proposals(masks: Any) -> list[dict[str, Any]]:
     if mask_array is None:
         return []
 
-    # Ensure 3D: [num_masks, H, W]
-    if mask_array.ndim == 2:
-        mask_array = np.expand_dims(mask_array, axis=0)
-
-    if mask_array.ndim != 3:
+    if mask_array.ndim < 2:
         return []
 
-    # Remove batch dim if present: [1, num_masks, H, W] → [num_masks, H, W]
-    if mask_array.ndim == 3 and mask_array.shape[0] == 1:
-        mask_array = mask_array[0]
+    if mask_array.ndim == 2:
+        mask_array = np.expand_dims(mask_array, axis=0)
+    else:
+        height, width = mask_array.shape[-2], mask_array.shape[-1]
+        mask_array = mask_array.reshape(-1, height, width)
 
     proposals: list[dict[str, Any]] = []
     for single_mask in mask_array: