facebookresearch / facebookresearch/sam3
sam3 supports image input as a prompt, and a box needs to be provided for input. Can we develop an interface where the input is changed to a numpy format of an image? I think this would be more flexible.
Open
- Dominant language
- Python
- Stars
- 11.7k
- Forks
- 1.8k
- PR merge metrics
- No merged PRs in 30d
Description
sam3 supports image input as a prompt, and a box needs to be provided for input. Can we develop an interface where the input is changed to a numpy format of an image? I think this would be more flexible.
Contributor guide
Research direction
Start by inspecting the SAM 3 image-prompt inference interface and the example notebooks to find where image and box inputs are defined. Determine the intended NumPy image shape and how it should coexist with the required box; done means the interface accepts a NumPy image input and the documented example works without changing existing prompt behavior.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- numpy, python
- Domain
- computer-vision, machine-learning
- Issue type
- Feature
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 35/100