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 β Academic Research
Dear Meta SAM 3 Team,
My request to access the SAM 3 Gating Group Collection was recently rejected without a stated reason. I would be grateful if you could manually review or reset my request.
I am a PhD researcher at Zhejiang University, China. My research focuses on computer-vision-assisted analysis of wooden interior environments. I plan to use SAM 3 locally for zero-shot semantic segmentation and human-reviewed annotation of architectural surfaces, including wooden walls, floors, ceilings, beams, and columns.
The model will be used exclusively for non-commercial academic research and offline dataset analysis. The project does not involve surveillance, biometric identification, military applications, or redistribution of model weights or credentials. I will comply with the applicable license terms, Meta policies, and Hugging Face terms.
Hugging Face username: Eurus
Affiliation: Zhejiang University
Position: PhD Researcher
Intended use: Non-commercial academic research and architectural image segmentation
Please let me know if any additional identity or institutional information is required.
Thank you for your consideration.
Best regards,
Xintong Zhu