SAM 2: Segment Anything in Images and Videos • Hacker News Board

minimaxir wrote: post #14

The web demo is actually pretty neat: https://sam2.metademolab.com/demo I selected each shoe as individual objects and the model was able to segment them even as they overlapped.

It's super fun! I used it on a video of my new cactus tweezers: https://simonwillison.net/2024/Jul/29/sam-2/

Re: SAM 2: Segment Anything in Images and Videos

#16

Post by rocauc » Tue, Jul 30, 2024, 12:15 AM UTC

simonw wrote: post #5

Has anyone built anything cool with the original SAM? What did you build?

One thing its enabled is automated annotations for segmentation, even on out-of-distribution examples. e.g. in the first 7 months of SAM, users on Roboflow used SAM-powered labeling to label over 13 million images, saving over ~21 years[0] of labeling time. That doesn't include labeling from self hosting autodistill[1] for automated annotation either.

[0] based on comparing avg labeling session time on individual polygon creation vs SAM-powered polygon examples [1] https://github.com/autodistill/autodistill

Re: SAM 2: Segment Anything in Images and Videos

#17

Post by TheHumanist » Tue, Jul 30, 2024, 12:22 AM UTC

acacac wrote: post #9

nravi20 wrote: post #2

Hi from the Segment Anything team! Today we’re releasing Segment Anything Model 2! It's the first unified model for real-time promptable object segmentation in images and videos! We're releasing the code, models, dataset, research paper and a demo! We're excited to see what everyone builds! https://ai.meta.com/blog/segment-anything-2/

will the model ever be extended to being able to segment audio (eg. different people talking, different instruments in a soundtrack?)

That would be really cool to try out. I hope someone is doing that.

Re: SAM 2: Segment Anything in Images and Videos

#18

Post by mrdjtek » Tue, Jul 30, 2024, 12:26 AM UTC

acacac wrote: post #9

nravi20 wrote: post #2

Hi from the Segment Anything team! Today we’re releasing Segment Anything Model 2! It's the first unified model for real-time promptable object segmentation in images and videos! We're releasing the code, models, dataset, research paper and a demo! We're excited to see what everyone builds! https://ai.meta.com/blog/segment-anything-2/

will the model ever be extended to being able to segment audio (eg. different people talking, different instruments in a soundtrack?)

There are a ton of models that do Stemming like this. We use them all the time. Lookup MvSep on Replicate.com

Re: SAM 2: Segment Anything in Images and Videos

#19

Post by Imnimo » Tue, Jul 30, 2024, 12:28 AM UTC

I think the first SAM is the open source model I've gotten the most mileage out of. Very excited to play around with SAM2!

Re: SAM 2: Segment Anything in Images and Videos

#20

Post by ed » Tue, Jul 30, 2024, 12:29 AM UTC

nravi20 wrote: post #2

Hi from the Segment Anything team! Today we’re releasing Segment Anything Model 2! It's the first unified model for real-time promptable object segmentation in images and videos! We're releasing the code, models, dataset, research paper and a demo! We're excited to see what everyone builds! https://ai.meta.com/blog/segment-anything-2/

Grounded SAM has become an essential tool in my toolbox (for others: it lets you mask any image using a text prompt, only). HUGE thank you to the team at Meta, I can't wait to try SAM2!