refactor(pipeline): integrate SAM segmentation and modularize model loading

mini-nav/configs/config.yaml

@@ -1,10 +1,11 @@
 model:
-  name: "facebook/dinov2-large"
+  dino_model: "facebook/dinov2-large"
   compression_dim: 512
   device: "auto" # auto-detect GPU
   sam_model: "facebook/sam2.1-hiera-large" # SAM model name
   sam_min_mask_area: 100 # Minimum mask area threshold
   sam_max_masks: 10 # Maximum number of masks to keep
+  sam_points_per_batch: 64
   compressor_path: null # Path to trained HashCompressor weights (optional)
 
 output:

mini-nav/configs/models.py

@@ -3,7 +3,7 @@
 from pathlib import Path
 from typing import Literal, Optional
 
-from pydantic import BaseModel, ConfigDict, Field, field_validator
+from pydantic import AliasChoices, BaseModel, ConfigDict, Field, field_validator
 
 
 class ModelConfig(BaseModel):
@@ -11,7 +11,10 @@ class ModelConfig(BaseModel):
 
     model_config = ConfigDict(extra="ignore")
 
-    dino_model: str = "facebook/dinov2-large"
+    dino_model: str = Field(
+        default="facebook/dinov2-large",
+        validation_alias=AliasChoices("dino_model", "name"),
+    )
     compression_dim: int = Field(
         default=512, gt=0, description="Output feature dimension"
     )
@@ -26,6 +29,11 @@ class ModelConfig(BaseModel):
     sam_max_masks: int = Field(
         default=10, gt=0, description="Maximum number of masks to keep"
     )
+    sam_points_per_batch: int = Field(
+        default=64,
+        gt=0,
+        description="SAM2 mask generation batch size for prompt points",
+    )
     compressor_path: Optional[str] = Field(
         default=None, description="Path to trained HashCompressor weights"
     )