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
Hello SAM 3 team,
My Hugging Face username is bsympgt.
I am an undergraduate student in Automation at Inner Mongolia University, working on non-commercial academic research in visual-language navigation.
I am currently reproducing OpenFrontier: General Navigation with Visual-Language Grounded Frontiers (RSS 2026). Its official implementation uses the original facebook/sam3 checkpoint for image segmentation.
My access request was rejected, and Hugging Face no longer allows me to submit the access form again. Could you please manually review my request or reset it to pending so that I can provide any additional information required?
Intended use:
- Non-commercial academic research and learning
- Reproduction and evaluation of OpenFrontier
- No redistribution of the SAM 3 checkpoint
- Full compliance with the model license and usage terms
Hugging Face username: bsympgt
Affiliation: Inner Mongolia University
Country/Region: China
Thank you very much for your time and consideration.