Inspection Tool

Use this tool to analyze dependencies among cameras in a scene.

Inspection is robust when verifying where to add images and what are the good and weak points of a scene. It might help you to find more optimal configurations for your cameras and so on. In other words, use this tool to analyze dependencies among cameras in a scene.

Where to find the Inspect tool: SCENE 3D/TOOLS tab - in the part Registration & Sparse Point Cloud. You can also simply press the letter I key while working in the 3Ds scene view.


There are three methods of inspection that you can use:

Camera relations

When using this approach, cameras are connected into virtual components based on their mutual connections and the defined settings. The cameras in the same virtual components are marked with the same color. If there are several virtual (color) components created, then the connection among the cameras from these separate components could be more stable, and we recommend adding images in these areas.


In the picture below, you can see a majority of cameras connected to one virtual component, three pink cameras connected to the second virtual component (in the red box), and separate cameras marked with different colors, not connected to any component. In such disconnected areas, it is recommended to add more images in order to make the connections more stable.


The color scale for the edges (connections among cameras) is as follows:


Point cloud uncertainty

Inspection Uncertainty

In the following picture, the areas with more red points are considered to have higher uncertainty and, therefore, lower precision. Add more images in such areas to improve the precision:

Inspection Example>

Uncertainty of points is displayed in this color scale:


Misalignment detection

This option enables you to find misaligned cameras or weak spots in your scene.


After the Misalignment detection was selected, the color of points in the 3Ds view will split into multiple colors. Blue colored points represent the correctly aligned points, while red points or points of a different color than blue are the ones RealityCapture calculated as misaligned.

Each set of points represents a "misaligned component", which cannot be seen in the 1Ds view, but is related to the Inspection tool. With this you can adjust the use of control points to correct the alignment and create a single component with higher accuracy.

Random colored cameras (misaligned cameras) are also going to be displayed in 3Ds view. These cameras should be larger than the cameras which represent the inputs. If you click on one of the misaligned cameras, cameras related to it will be selected. Their color represents their accuracy. Light blue cameras are the ones RealityCapture deems as the ones with lower accuracy, and grey cameras should have good accuracy. Cameras may be connected with white lines, which are usually heading toward the problematic camera.

See also: