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 Access: Using SAM 3 for Segmentation in World Model Evaluation
#324
by KSZG - opened
My name is Chen Kaiwei. My Hugging Face username is KSZG. I am a graduate student at Zhejiang University, working on Embodied AI and World Models.
I am currently conducting research on evaluating world models through physical scene understanding. In this project, I plan to use SAM 3 for promptable segmentation on 3D-reconstructed scenes to analyze object-level semantics and validate the physical consistency of world model predictions.
The research is conducted within a university setting and is intended solely for scientific and academic purposes. I will fully comply with the SAM 3 license and all applicable usage restrictions.
I would greatly appreciate it if you could approve my access request.