How to do segmentation on point cloud?
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 3.8k
- Forks
- 899
- PR merge metrics
- No merged PRs in 30d
Description
It can be seen here that the class information in the PLY file as the 7th value of each point.
https://github.com/mapillary/OpenSfM/issues/506#issuecomment-799298879
You can see from the picture that mine are in the 10th value
However, the class for all the 3d points are all 0 for my Berlin merged.ply file, when there are already prepared masks.
Is there anything I can do to let the masks do its job?
Or is there any way I can edit the class value so that it is not 0 for every point?
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 reviewing the referenced OpenSfM issue and comparing the 7th and 10th values in the Berlin merged.ply file. Trace how the prepared masks and PLY class values are expected to interact, then determine whether the masks populate the class field. Done means identifying the cause of the all-zero class values and documenting or reproducing the required correction.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- computer-vision
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100