---
title: 'SAM 2: Segment Anything in Images and Videos'
license: CC-BY-4.0
license_url: https://creativecommons.org/licenses/by/4.0/
license_note: 'paper is arXiv non-exclusive distribution license (verified on arXiv abs page 2026-11-12); this pointer note is our own words and is CC BY 4.0; we link to the paper rather than reproduce it'
source: https://iinventedlight.com/library/notes/2408-00714-sam-2.md
source_license: 'arXiv non-exclusive distribution license'
attribution: 'Pointer by iinventedlight (AI-assisted). Source: Nikhila Ravi, Valentin Gabeur, Yuan-Ting Hu, and 15 coauthors (listed on the arXiv abs page), SAM 2: Segment Anything in Images and Videos (arXiv non-exclusive distribution license). This note links to the paper rather than reproducing it.'
author: 'iinventedlight (AI-assisted)'
date: 2026-11-12
status: published
approved_by: "Cole Withington, 2026-11-12 14:44 PT, Librarian chat widget t51s316: \"Yes, publish all 100 second-list arXiv notes\""
checked_on: 2026-11-12
as_of: 2026-11-12
confidence: medium
untested: 'Pointer note only. Paper not reproduced. Abs page and license checked 2026-11-12.'
category: arxiv
topic_area: 'ai-research: multimodal'
tags: arxiv, multimodal, segmentation, video
arxiv_id: 2408.00714
alias: 2408.00714-sam-2
type: pointer
format: pointer
sources:
  - id: S1
    title: 'SAM 2: Segment Anything in Images and Videos'
    publisher: arXiv
    authors: 'Nikhila Ravi, Valentin Gabeur, Yuan-Ting Hu, and 15 coauthors (listed on the arXiv abs page)'
    url: https://arxiv.org/abs/2408.00714
    version_read: 'v2 (28 Oct 2024)'
    accessed: 2026-11-12
    license: 'arXiv non-exclusive distribution license'
---
# SAM 2: Segment Anything in Images and Videos

## Summary
[SAM 2: Segment Anything in Images and Videos](https://arxiv.org/abs/2408.00714) (2024) extends Segment Anything from still images to images and video. SAM 2 is a promptable segmentation foundation model with a streaming memory, trained with a data engine that collects a large video segmentation set through interactive annotation.

What it introduced: a single model for promptable segmentation across images and video, using a simple transformer with memory so that video can be processed in a streaming, real-time way rather than frame by frame in isolation.

What it led to: the current default starting point for promptable image and video segmentation, building on the original Segment Anything release. Live note: [2304-02643-segment-anything](https://iinventedlight.com/library/notes/2304-02643-segment-anything/).

Use it when you already know the first SAM paper and want the video follow-up. Where to read it: https://arxiv.org/abs/2408.00714 (v2 (28 Oct 2024)).

The paper is posted on arXiv under the arXiv non-exclusive distribution license. This note links to it rather than reproducing it. The note itself is CC BY 4.0.

License: this note is CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). Pointer by iinventedlight (AI-assisted). Paper license: arXiv non-exclusive distribution; this note links to it and does not reproduce it.

---

Agents: [/agents.md](/agents.md) | [/.well-known/agent-library.json](/.well-known/agent-library.json).
