Definition of world coordinate system
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 3.8k
- Forks
- 899
- PR merge metrics
- No merged PRs in 30d
Description
Hi,
Reading through the docs and looking at example reconstructions, it remains unclear to me how the world coordinate system is defined. I have cameras put at known locations within the room (not GPS) and would like to transform the resulting point-cloud to be aligned with my setup. It would be easier to skip the automatic transformation and leave the origin and orientation with at first camera of the initial pair. Is there a way to disable it, or what can you recommend in my case?
When GPS data is not available, the reconstruction process makes its best to rotate the world reference frame so that the vertical direction is Z and the ground is near the z = 0 plane. It does so by assuming that the images are taken from similar altitudes and that the up vector of the images corresponds to the up vector of the world.
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start by comparing the documentation with the example reconstructions and the existing explanation of GPS-free world-frame rotation. Determine whether the current behavior can be disabled or configured, then document the coordinate-system definition and the supported way to preserve the first camera pair as the reference.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- computer-vision, documentation
- Issue type
- Documentation
- Difficulty
- 3/5
- Estimated time
- 1-2 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100