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 of Rejected SAM 3 Access β AIMovie 3DGS Project
Hello SAM 3 team,
My Hugging Face username is: urm15
My access request to facebook/sam3 was rejected, but no specific rejection reason was shown on the model page.
I am developing an engineering/research project called AIMovie. The project uses text-prompted segmentation to identify large furniture objects such as beds, tables, sofas, and fitness equipment in indoor 3D Gaussian Splatting scenes. The segmentation results are used to construct simplified interaction and collision geometry.
Project repository:
https://github.com/lsy13754785196-max/AImovie
Intended use:
- Research and software development
- Text-prompted segmentation of indoor furniture
- Multi-view mask association with 3D Gaussian Splatting
- No checkpoint redistribution
- The checkpoint will only be stored and used on my secured AutoDL development server
- I will comply with the applicable SAM license and model terms
Could you please manually review my application again, or let me know whether any information in my request was incomplete or ineligible?
Thank you for your time.