feat(PCSegSAM2): auto pointcloud segmentation using SAM2 and GroundingDino #44
+20,213
−0
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Summary
Since we lack large segmentation databases I leveraged the use of SAM2, GroundingDino, and the vehicle calibration to segment pointclouds using open source foundation models.
This project allows to:
This project essentially copies
https://github.com/IDEA-Research/Grounded-SAM-2/tree/main
and implement the necessary features.
I asked @scepter914 and there was no reticence to just paste all the required code as long as there was no issues with the licences.
Change point
Add a new project for automatic pointcloud segmentation
Note
Since it is a new project with an independent docker, it does not affect any other project in the codebase
Test performed
Build docker, run all tasks presented in the README, and segmented t4data (during April)