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") - Notebooks
- Google Colab
- Kaggle
Request for reconsideration of rejected SAM 3 access
Dear Meta SAM 3 Team,
My access request to the SAM 3 Gating Group Collection was recently rejected. I would be grateful if you could reconsider or reset my request.
I am a graduate student at Beijing Institute of Technology, China. My research focuses on embodied AI, robot learning, and egocentric manipulation data.
I plan to use SAM 3.1 for academic and research-oriented evaluation of hand and forearm segmentation in egocentric manipulation videos. Specifically, I am conducting a small-scale MVP study that removes human hands from EgoDex/EgoVerse video frames and replaces them with simulated robotic grippers. SAM 3.1 will only be used for segmentation and tracking evaluation.
I will comply with the applicable license terms, Meta policies, and Hugging Face terms. The model weights and access credentials will not be redistributed.
Hugging Face username: Ricky0626
Affiliation: Beijing Institute of Technology
Position: Graduate Student
Intended use: Academic research and non-commercial MVP evaluation
Please let me know if any additional information is required.
Thank you for your consideration.
Best regards,
Chengrui Tao