Seonglae ChoSAM
Browser WASM
very fast
SAM2
Introducing SAM 2: The next generation of Meta Segment Anything Model for videos and images
Today, we’re publicly releasing SAM 2, the first-ever unified model for segmenting anything in videos and images.
https://ai.meta.com/blog/segment-anything-2/
WebGPU
Segment Anything WebGPU - a Hugging Face Space by Xenova
Discover amazing ML apps made by the community
https://huggingface.co/spaces/Xenova/segment-anything-webgpu
arxiv.org
https://arxiv.org/abs/2304.02643
Introducing Segment Anything
We're releasing the Segment Anything Model (SAM) — a step toward the first foundation model for image segmentation — and the SA-1B dataset.
https://ai.facebook.com/blog/segment-anything-foundation-model-image-segmentation/
Segment Anything
Meta AI Computer Vision Research
https://segment-anything.com/
SA-V Dataset
SA-V | Meta AI Research
SA-V is a dataset designed for training general-purpose object segmentation models from open world videos. The dataset was introduced in our paper “Segment Anything 2”. .
https://ai.meta.com/datasets/segment-anything-video/
Introducing Segment Anything
We're releasing the Segment Anything Model (SAM) — a step toward the first foundation model for image segmentation — and the SA-1B dataset.
https://ai.facebook.com/blog/segment-anything-foundation-model-image-segmentation/
SAM 3.1: Faster and More Accessible Real-Time Video Detection and Tracking With Multiplexing and Global Reasoning (Object Multiplexing)
SAM 3.1: Faster and More Accessible Real-Time Video Detection and Tracking With Multiplexing and Global Reasoning
We’ve seen incredible adoption of SAM 3 over the last few months, and during that time, we’ve been working behind the scenes on updates to improve video processing efficiency. Today, we’re pleased to introduce SAM 3.1.
https://ai.meta.com/blog/segment-anything-model-3/
