Inspection Tool

Hi! I am running a model from a data set of about 400 photos and would like to try to use the “Inspect Quality” tool to refine my model. I’ve aligned the photos, but when I hotkey “I” or manually click “Inspect Quality,” my point cloud disappears and the network of blue lines I think I’m supposed to see doesn’t show up. Please advise. Thank you!

Dear CarrC23,

that could mean, that you don’t have misaligned images.

You can change this settings to see changes in Inspect Quality tool:

After you will select the Misalignment detection, the color of points in the 3d view will split into multiple colors:

  • Blue points  - are points that are aligned correctly
  • Red or points with other colors  - are points that RealityCapture thinks are misaligned

Point cloud colors
Each set of points represents a “misaligned component” (you will not see these components in the 1ds view. Only in the inspection tool), this way you can adjust the use of control points to correct the alignment and create a single component with higher accuracy.

Camera colors
You will also see colored Misaligned cameras (these are even a little bit larger). After you will click on them this will select all related cameras of that misaligned component.
Grey cameras represent cameras that RealityCapture thinks have good accuracy.
White lines (camera relations) are usually heading toward the problematic camera position

Settings explanations

Misaligned points threshold

Marks with a color the given percentage of points that are the most likely misaligned. If you will choose for example a value of 50%, misalignment tool will mark 50% of the most misaligned points.

Misaligned camera pairs threshold

Displays a given percentage of the most misaligned camera pairs for each misaligned camera group. If you will choose for example a value of 50%, misalignment tool will mark 50% of the most misaligned camera relations for each detected camera group.

Misalignment detector sensitivity

Sets the sensitivity of the misalignment detector. Higher sensitivity takes more computational time but will generate more data to work with. In some cases, the higher sensitivity can create false positives.