Instructions to use facebook/sam3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use facebook/sam3 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("mask-generation", model="facebook/sam3")# Load model directly from transformers import AutoProcessor, AutoModel processor = AutoProcessor.from_pretrained("facebook/sam3") model = AutoModel.from_pretrained("facebook/sam3", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Request for Manual Review / Reset of Rejected SAM 3 Access
Hello Meta SAM 3 Team,
My access request for the facebook/sam3 repository was recently rejected. I would like to kindly request a manual review or a reset of my rejected access status so that I can submit the application again if necessary.
I am working on non-commercial research in robotics, embodied AI, and Real2Sim scene reconstruction.
My intended use of SAM 3 includes:
- object segmentation and tracking in robot demonstration videos;
- identifying task-interaction objects and supporting environment elements;
- semantic annotation of RGB/RGB-D data;
- preprocessing for 3D reconstruction and simulation environment generation;
- research experiments related to robotic manipulation and embodied perception.
The model will be used locally for research and evaluation purposes only. I will not redistribute the SAM 3 model weights or provide unauthorized access to the model.
I will comply with the SAM 3 license, Meta policies, Hugging Face terms, and all applicable requirements.
Could you please manually reconsider my application, or reset my rejected access status so that I can submit the required information again?
Hugging Face username: YOUR_HUGGINGFACE_USERNAME
Affiliation: YOUR_COMPANY / UNIVERSITY / RESEARCH INSTITUTE
Role: YOUR_ROLE
Thank you very much for your time and consideration.