feat(scenegraph): add depth-based 3D positioning via pinhole projection

- Add bbox_depth_center position strategy in SceneGraphBuilder using depth
  at bbox centre and configurable camera_hfov_degrees for pinhole projection.
- Add optional depth_sensor_uuid to HabitatSimulatorConfig; create depth
  sensor spec alongside RGB sensor.
- Add camera_position/camera_rotation fields to RoomView; capture pose from
  sensor_states when depth sensor is available.
- Update flatten_room_views for backward compatibility with legacy tuple
  format.
- Wired in depth sensor and bbox_depth_center strategy in verification
  notebook.
- Add tests for depth sensor support and new position strategies.

notebooks/verification.py

@@ -24,10 +24,9 @@ def base_dependencies():
     """Basic dependencies for data processing."""
     import numpy as np
     import polars as pl
-    import torch
     from PIL import Image
 
-    return Image, np, pl, torch
+    return Image, np, pl
 
 
 @app.cell
@@ -99,16 +98,15 @@ def habitat_setup(HabitatSimulatorConfig, RoomNode, create_habitat_simulator, np
     views_per_room = 12
     meters_per_pixel = 0.05
 
-    sim, agent = create_habitat_simulator(
-        HabitatSimulatorConfig(
-            scene_path=_scene_path,
-            views_per_room=views_per_room,
-            image_size=_image_size,
-            sensor_height=1.5,
-            move_forward_step=0.25,
-            enable_physics=False,
-        )
+    habitat_config = HabitatSimulatorConfig(
+        scene_path=_scene_path,
+        views_per_room=views_per_room,
+        image_size=_image_size,
+        sensor_height=1.5,
+        move_forward_step=0.25,
+        enable_physics=False,
     )
+    sim, agent = create_habitat_simulator(habitat_config)
 
     room_nodes = []
     for idx in range(_num_rooms):
@@ -125,7 +123,7 @@ def habitat_setup(HabitatSimulatorConfig, RoomNode, create_habitat_simulator, np
     for _node in room_nodes:
         print(f"  {_node.room_id}: {_node.center}")
 
-    return agent, meters_per_pixel, room_nodes, sim, views_per_room
+    return agent, habitat_config, meters_per_pixel, room_nodes, sim, views_per_room
 
 
 @app.cell
@@ -164,6 +162,7 @@ def collect_views(
     agent,
     collect_room_views_by_room,
     flatten_room_views,
+    habitat_config,
     numpy_to_pil,
     room_nodes,
     sim,
@@ -174,6 +173,7 @@ def collect_views(
         sim=sim,
         room_nodes=room_nodes,
         views_per_room=views_per_room,
+        depth_sensor_uuid=habitat_config.depth_sensor_uuid,
     )
 
     room_views = flatten_room_views(all_room_views)
@@ -193,6 +193,7 @@ def build_scene_graph(
     SceneGraphBuildConfig,
     SceneGraphBuilder,
     cfg_manager,
+    habitat_config,
     mo,
     numpy_to_pil,
     pipeline,
@@ -207,7 +208,11 @@ def build_scene_graph(
 
     builder = SceneGraphBuilder(
         pipeline=pipeline,
-        config=SceneGraphBuildConfig(inference_batch_size=4),
+        config=SceneGraphBuildConfig(
+            inference_batch_size=4,
+            position_strategy="bbox_depth_center",
+            camera_hfov_degrees=habitat_config.hfov_degrees,
+        ),
     )
 
     pil_room_views = [
@@ -218,6 +223,8 @@ def build_scene_graph(
             depth=_view.depth,
             agent_position=_view.agent_position,
             agent_rotation=_view.agent_rotation,
+            camera_position=_view.camera_position,
+            camera_rotation=_view.camera_rotation,
         )
         for _view in room_views
     ]
@@ -303,6 +310,8 @@ def build_tables(pl, scene_graph):
             "position_x": float(obj.position[0]) if obj.position is not None else None,
             "position_y": float(obj.position[1]) if obj.position is not None else None,
             "position_z": float(obj.position[2]) if obj.position is not None else None,
+            "bbox_xyxy": str(obj.bbox_xyxy) if obj.bbox_xyxy is not None else None,
+            "position_confidence": obj.position_confidence,
         }
         for obj in scene_graph.objects.values()
     ]
@@ -313,6 +322,19 @@ def build_tables(pl, scene_graph):
     return objects_df, rooms_df
 
 
+@app.cell
+def display_tables(mo, objects_df, rooms_df):
+    mo.vstack(
+        [
+            mo.md("## Rooms"),
+            mo.ui.table(rooms_df),
+            mo.md("## Objects"),
+            mo.ui.table(objects_df),
+        ]
+    )
+    return
+
+
 @app.cell
 def upload_query(mo):
     file_upload = mo.ui.file(
@@ -329,7 +351,6 @@ def query_matching(
     Image,
     file_upload,
     mo,
-    object_images,
     pipeline,
     query_image_against_scene_graph,
     scene_graph,