跳过导航
Introducing Meta Segment Anything Model 2 (SAM 2) — the first unified model for real-time…
0:00 / 1:20

Introducing Meta Segment Anything Model 2 (SAM 2) — the first unified model for real-time…

AI at Meta

@AIatMeta88万 位关注者

在 X 上查看
6,863 个赞下载原帖

1,620,156 次观看

Introducing Meta Segment Anything Model 2 (SAM 2) — the first unified model for real-time, promptable object segmentation in images & videos. SAM 2 is available today under Apache 2.0 so that anyone can use it to build their own experiences Details ➡️

10 条评论

评论来自 X (Twitter) 上的原帖

  • AI at Meta 的头像

    @AIatMeta

    In addition to the new model, we’re also releasing SA-V, a dataset that’s 4.5x larger + has ~53x more annotations than the largest existing video segmentation dataset. We hope this work will help accelerate new computer vision research ➡️

    480 个赞

  • AI at Meta 的头像

    @AIatMeta

    Like the original SAM, SAM 2 can be applied out of the box to a diverse range of real-world use cases and we’re excited to see what developers build with it. Try the demo ➡️ Get the code ➡️

    374 个赞

  • Mckay Wrigley 的头像

    @mckaywrigley

    Legendary 7-day open source Meta run rn lfg

    167 个赞

  • Lex Fridman 的头像

    @lexfridman

    Wow, amazing!

    130 个赞

  • Dwayne 的头像

    @CtrlAltDwayne

    Wow. Meta are cooking gourmet Michelin star meals over here.

    100 个赞

  • rad ed 的头像

    @ed__rad

    inpainting is about to go crazy when its added to video with persistent object detection

    81 个赞

  • Indra 的头像

    @IndraVahan

    I like it. It's gonna save video editors a lot of time creating masks and rotoscoping. It's not perfect, but it saves us from Adobe CCs proprietary, lock-in roto tools. Thanks zucc.

    74 个赞

  • mansa musa 👑 的头像

    @mansam00sa

    This is wild! Advertisers are going to pay subscriptions to keep their products in videos lmao

    47 个赞

  • MindBranches 的头像

    @MindBranches

    Summary of the Meta SAM 2 announcement

    40 个赞

  • Amit Shukla 的头像

    @ashuklax

    Just when I thought I'm done reading 99 pages, you show up with another book. Grateful for the Apache license.

    15 个赞