Fix data generation error in the referencerun_fmb.py (#33)

(Closes MET-58)

## Background

Turns out I made a mistake when porting over the reference
implementation in #6, where
in the section that render the g round truth image, I dropped the code
that delete the light & camera nodes (because I thought that
`r.delete()` would delete everything regardless. However, without this
cleanup, it seems like `pyrender` always uses the first camera node to
render the image, so we end up with a sequence of identical input
images, which causes convergence issue.

This is fixed by placing back the cleanup code.

## Before & After

**Before the fix**:

Input depth image (generated by `pyrenderer`):

<img width="558" height="423" alt="image"
src="https://github.com/user-attachments/assets/6ed682a2-b219-4b3d-87aa-3ed6b335322a"
/>

FMB optimized output:

<img width="551" height="427" alt="image"
src="https://github.com/user-attachments/assets/433610bd-2371-43d9-80dd-a567cdbf5d43"
/>

**After the fix**:

Input depth image:

<img width="558" height="423" alt="image"
src="https://github.com/user-attachments/assets/1c005a24-1659-4b0a-be0d-97faf00b5d11"
/>

FMB optimized output:

<img width="551" height="427" alt="image"
src="https://github.com/user-attachments/assets/943ed577-b941-4531-9712-114a82ee7c86"
/>

Author: horizon-blue

examples/run_fmb.py

@@ -384,6 +384,10 @@ def main():
         ref_colors.append(color)
         ref_depths.append(target_depth)
 
+        for node in list(scene.light_nodes):
+            scene.remove_node(node)
+        for node in list(scene.camera_nodes):
+            scene.remove_node(node)
         r.delete()
 
     render_time = (time.perf_counter() - render_start) * 1000