facebookresearch / facebookresearch/sam3

Weird outputs for point prompts

Open
#241 8 comments 0 reactions 0 assignees View on GitHub
Dominant language
Python
Stars
11.7k
Forks
1.8k
PR merge metrics
No merged PRs in 30d

Description

I tried the SAM3 model for point prompts. When compared to SAM2, it produced such outputs frequently.

Image

Contributor guide

Open the contributing guide

Research direction

The issue names no source file, test, prompt coordinates, input image, checkpoint, or inference configuration. Start by collecting those details and reproducing the point-prompt result against SAM2; done means determining whether the output is a SAM3 defect or expected behavior and documenting the evidence.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
computer-vision
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.