Efficient6D-SAM-VLM-to-Grasp
Our Repo is constantly being updated
Repo list :
- An Efficient RGB-D features extractor to category-level and instance-level 6D pose estimation.
- Bidirectional cross attentin fusion with rgb-point cloud and globe-local features.
- An end-to-end category level pose estimation inference scripts that includes real-time segmentation of SAM. (Free of shape piror)
- SAM-VLM to grasping task with 3DBBOX (Using Azure Kinect or Realsense).
![output_video](https://github.com/houph4/Efficient6D-SAM-VLM-to-Grasping-task/assets/90714020/a6a887d7-95bc-4993-a1be-d33d1fde10dc)