#46 · Primary category： Computer Vision
sam3
The repository provides code for running inference and finetuning with the Meta Segment Anything Model 3 (SAM 3), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.
Project last updated：08/26/26
GitHub Stars
11.5K
Forks
1.7K
Contributors
27
License
Other
Why we included this project
Picking one specific object out of an image or video frame is harder than it sounds, and SAM 3 is built for exactly that. It carries Meta's segment-anything line forward by letting text or visual prompts drive the segmentation, so you can ask for 'the red mug' instead of drawing a box around it and hoping the model guesses right. The repo covers more than plain inference: it includes code for fine-tuning the model on your own data, download links for the trained checkpoints, and example notebooks that walk through both paths. That matters when your task is niche enough that the stock weights don't cut it. Teams doing interactive editing, video object tracking, or automated visual QA get a practical starting point rather than a toy demo.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
opencv
Open Source Computer Vision Library
RuView
π RuView turns commodity WiFi signals into real-time spatial intelligence, vital sign monitoring, and presence detection — all without a single pixel of video.
PaddleOCR
Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.
MinerU
Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.
tesseract
Tesseract Open Source OCR Engine (main repository)