Meshroom
Meshroom copied to clipboard
Add constraint to get absolute scale reconstruction
In structure-from-motion with a single camera the scene can be only recovered up to a scale. However if you have more information such as baseline of the camera motion or the dimension of at least one element in the scene, the absolute scale can be reconstructed. Is there a way to add such constraints in meshroom?
You can have a look at the SfMTransform node.
You can put CCTag markers in the scene with a known distances between them to rescale your scene precisely. There are also other options to rescale your scene globally based on the bounding box of all cameras or all points, but that's not really reliable in practice.
- https://github.com/alicevision/meshroom/wiki/CCTAG-scaling
This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your contributions.