Loading video...

Video Failed to Load

Go Home

🚨 Meta introduces 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 ➡️

_vztu's profile picture

Zhengzhong Tu

7,334 subscribers

181,288 views • 1 year ago •via X (Twitter)

EducationScience & Technology
LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Today we're releasing the Segment Anything Model (SAM) — a step toward the first foundation model for image segmentation. SAM is capable of one-click segmentation of any object from any photo or video + zero-shot transfer to other segmentation tasks ➡️
0:15

Today we're releasing the Segment Anything Model (SAM) — a step toward the first foundation model for image segmentation. SAM is capable of one-click segmentation of any object from any photo or video + zero-shot transfer to other segmentation tasks ➡️

AI at Meta

3,570,378 views • 3 years ago

A challenge for ML diagnosticians: The patient, Segment-Anything-Model-2 (SAM-2), is presenting with two prominent symptoms: Symptom 1) Extremely high-magnitude tokens spread evenly across spatial dimensions.
0:18

A challenge for ML diagnosticians: The patient, Segment-Anything-Model-2 (SAM-2), is presenting with two prominent symptoms: Symptom 1) Extremely high-magnitude tokens spread evenly across spatial dimensions.

Rudy Gilman

25,936 views • 1 year ago

Meta dropped not just SAM-3 yesterday but also SAM-3D (for objects and humans)🤯 SAM 3D Body is a promptable model for recovering full-body 3D human meshes from a single image. Seems to be the new SOTA
0:16

Meta dropped not just SAM-3 yesterday but also SAM-3D (for objects and humans)🤯 SAM 3D Body is a promptable model for recovering full-body 3D human meshes from a single image. Seems to be the new SOTA

Niels Rogge

125,088 views • 7 months ago

ੈ✩‧༺ 2.0 MODEL REVEAL ༻*✩‧₊˚ 3, 2, 1 Space ship ready to launch~🚀 Galateia 2.0 Model is finally here! 💜& 🔁 to reveal the model! #GalateiaStella #VtuberID #Vtuber
0:15

ੈ✩‧༺ 2.0 MODEL REVEAL ༻*✩‧₊˚ 3, 2, 1 Space ship ready to launch~🚀 Galateia 2.0 Model is finally here! 💜& 🔁 to reveal the model! #GalateiaStella #VtuberID #Vtuber

GALATEIA⭐️

14,580 views • 2 years ago

Did you know we're working with environmental survey teams to improve flood detection? Our Segment Anything Model (SAM) is being used to identify minute changes in water conditions from satellite images—we hope this faster analysis can contribute to better rapid response and keep communities safer.
0:16

Did you know we're working with environmental survey teams to improve flood detection? Our Segment Anything Model (SAM) is being used to identify minute changes in water conditions from satellite images—we hope this faster analysis can contribute to better rapid response and keep communities safer.

Meta

157,982 views • 4 months ago

just updated my Segment Anything 2 (SAM2) Hugging Face space now you can run the model in two modes - box prompt and automatic mask generation; I'll try to add short video segmentation today link to space if you want to have some fun:
0:15

just updated my Segment Anything 2 (SAM2) Hugging Face space now you can run the model in two modes - box prompt and automatic mask generation; I'll try to add short video segmentation today link to space if you want to have some fun:

SkalskiP

16,075 views • 1 year ago

segment-geospatial v0.3.0 is out - segmenting satellite imagery with the Segment Anything Model (SAM). GitHub: Docs: Notebook: #segmentanything #deeplearning #geopython #geospatial
0:12

segment-geospatial v0.3.0 is out - segmenting satellite imagery with the Segment Anything Model (SAM). GitHub: Docs: Notebook: #segmentanything #deeplearning #geopython #geospatial

Qiusheng Wu

207,094 views • 3 years ago

Meta's SAM 3 is a beast. before: collect data, train custom object detector, use tracker to estimate object motion - days now: track anything with text prompt - seconds real-time object detection will never be the same.
0:15

Meta's SAM 3 is a beast. before: collect data, train custom object detector, use tracker to estimate object motion - days now: track anything with text prompt - seconds real-time object detection will never be the same.

Akshay 🚀

31,412 views • 7 months ago

Tree extraction from satellite imagery using segment-geospatial v0.5 and the Segment Anything Model (SAM) - by Lucas Prado Osco LinkedIn post: Notebook: #geospatial #segmentanything
0:10

Tree extraction from satellite imagery using segment-geospatial v0.5 and the Segment Anything Model (SAM) - by Lucas Prado Osco LinkedIn post: Notebook: #geospatial #segmentanything

Qiusheng Wu

40,463 views • 3 years ago

Now that Gemini Embedding 2 is GA, let’s explore what the model unlocks — from agentic multimodal RAG to visual search — as it maps text, images, video, audio, and documents into a unified embedding space.
0:14

Now that Gemini Embedding 2 is GA, let’s explore what the model unlocks — from agentic multimodal RAG to visual search — as it maps text, images, video, audio, and documents into a unified embedding space.

Google AI Developers

62,539 views • 1 month ago

Here are the steps to create this animation: 1. Design and model your own mech in Plasticity. 2. Import the model into the animation software 3ds Max. 3. Create the animation on your own. 4. Render and export the monochrome model animation. 5. Make the final render for reference. 6. Use Seedance 2 to re-render your monochrome model animation according to the reference render you provided. Summary: In this workflow, Seedance 2 acts as a renderer that saves you hours of rendering time. All other work has to be done manually by yourself. Don’t blindly believe that AI can fully produce mech animations for you — it simply cannot do that.
0:18

Here are the steps to create this animation: 1. Design and model your own mech in Plasticity. 2. Import the model into the animation software 3ds Max. 3. Create the animation on your own. 4. Render and export the monochrome model animation. 5. Make the final render for reference. 6. Use Seedance 2 to re-render your monochrome model animation according to the reference render you provided. Summary: In this workflow, Seedance 2 acts as a renderer that saves you hours of rendering time. All other work has to be done manually by yourself. Don’t blindly believe that AI can fully produce mech animations for you — it simply cannot do that.

LAS91214

45,537 views • 28 days ago

🚀 The Segment Anything Model (SAM) has been upgraded to SAM2, featuring an efficient image encoder for segmenting images and videos. But does SAM2 outperform SAM1 in medical image and video segmentation? We're thrilled to present our paper "Segment Anything in Medical Images and Videos: Benchmark and Deployment"! We comprehensively benchmark SAM2 across 11 medical image modalities and videos. 📄 Paper: 💻 Code: **Highlights:** 1. SAM2 doesn’t always outperform SAM1 in 2D medical images, but excels in video segmentation, making it more accurate and efficient for 3D images, such as CT and MR scans. 2. MedSAM still outperforms SAM2 on most 2D modalities, but SAM2 surpasses MedSAM for 3D image segmentation in a slice-by-slice approach. 3. Segmentation performance varies with model size; sometimes the smallest model outperforms larger ones. 4. Fine-tuning SAM2 significantly boosts its performance for medical image segmentation. While SAM2 may struggle with challenging objects that have unclear boundaries or low contrast, it excels in generating good initial segmentation masks for common medical images and videos. However, the official interface doesn’t support medical data formats and has limitations on video length. To address this, we've developed a 3D Slicer Plugin and Gradio API for efficient 3D medical image and video segmentation. We invite you to try them out and provide feedback! 🔧 Deployment: - 3D Slicer Plugin: - Gradio API: (Note: Due to GPU limitations, the online API is available for only 12 hours and may be slow. We highly recommend deploying the Gradio API with your own computing resources: A big shoutout to Jun Ma (JunMa) who recently joined our UHN AI hub (UHN AI Hub) as Machine Learning Lead, and kudos to all co-authors: Sumin Kim, Feifei Li, Mohammed Baharoon (Mohammed Baharoon), Reza Asakereh, and Hongwei Lyu! This is true teamwork! Looking forward to collaborating with the community to advance 3D medical image and video segmentation foundation models! University Health Network U of T Department of Computer Science Department of Laboratory Medicine & Pathobiology Temerty Centre for AI in Medicine (T-CAIREM) Vector Institute #MedTech #AIinHealthcare #DeepLearning #MedicalImaging #SAM2 #MedSAM #AIResearch
0:22

🚀 The Segment Anything Model (SAM) has been upgraded to SAM2, featuring an efficient image encoder for segmenting images and videos. But does SAM2 outperform SAM1 in medical image and video segmentation? We're thrilled to present our paper "Segment Anything in Medical Images and Videos: Benchmark and Deployment"! We comprehensively benchmark SAM2 across 11 medical image modalities and videos. 📄 Paper: 💻 Code: **Highlights:** 1. SAM2 doesn’t always outperform SAM1 in 2D medical images, but excels in video segmentation, making it more accurate and efficient for 3D images, such as CT and MR scans. 2. MedSAM still outperforms SAM2 on most 2D modalities, but SAM2 surpasses MedSAM for 3D image segmentation in a slice-by-slice approach. 3. Segmentation performance varies with model size; sometimes the smallest model outperforms larger ones. 4. Fine-tuning SAM2 significantly boosts its performance for medical image segmentation. While SAM2 may struggle with challenging objects that have unclear boundaries or low contrast, it excels in generating good initial segmentation masks for common medical images and videos. However, the official interface doesn’t support medical data formats and has limitations on video length. To address this, we've developed a 3D Slicer Plugin and Gradio API for efficient 3D medical image and video segmentation. We invite you to try them out and provide feedback! 🔧 Deployment: - 3D Slicer Plugin: - Gradio API: (Note: Due to GPU limitations, the online API is available for only 12 hours and may be slow. We highly recommend deploying the Gradio API with your own computing resources: A big shoutout to Jun Ma (JunMa) who recently joined our UHN AI hub (UHN AI Hub) as Machine Learning Lead, and kudos to all co-authors: Sumin Kim, Feifei Li, Mohammed Baharoon (Mohammed Baharoon), Reza Asakereh, and Hongwei Lyu! This is true teamwork! Looking forward to collaborating with the community to advance 3D medical image and video segmentation foundation models! University Health Network U of T Department of Computer Science Department of Laboratory Medicine & Pathobiology Temerty Centre for AI in Medicine (T-CAIREM) Vector Institute #MedTech #AIinHealthcare #DeepLearning #MedicalImaging #SAM2 #MedSAM #AIResearch

Bo Wang

178,455 views • 1 year ago

T4 | Zags 2, Lopes 1 Sam Stem comes through with the RBI double! 2-for-3 so far in his first career start. Wow.
0:15

T4 | Zags 2, Lopes 1 Sam Stem comes through with the RBI double! 2-for-3 so far in his first career start. Wow.

Gonzaga Baseball

25,210 views • 3 years ago

Our latest and most capable image generation model is available in Gemini: Meet Imagen 4. Everyone can make images for free in the Gemini App today.
0:16

Our latest and most capable image generation model is available in Gemini: Meet Imagen 4. Everyone can make images for free in the Gemini App today.

Google Gemini

26,490,824 views • 1 year ago

this is the BEST vision language model I have ever tried! Aria is a new model by Rhymes.AI: a 25.3B multimodal model that can take image/video inputs 🤩 They release the model with Apache-2.0 license and fine-tuning scripts as well 👏 I tested it extensively, keep reading to learn more 🧶
0:10

this is the BEST vision language model I have ever tried! Aria is a new model by Rhymes.AI: a 25.3B multimodal model that can take image/video inputs 🤩 They release the model with Apache-2.0 license and fine-tuning scripts as well 👏 I tested it extensively, keep reading to learn more 🧶

merve

176,047 views • 1 year ago

Sam Reinhart is OUT for the rest of Game 2 after this hit from Sebastian Aho in the first
0:12

Sam Reinhart is OUT for the rest of Game 2 after this hit from Sebastian Aho in the first

B/R Open Ice

329,826 views • 1 year ago

🚀 Wan 2.6 is now live on fal ! • Text-to-Video & Image-to-Video up to 1080p • Up to 15 second generations • Multi-shot video with intelligent scene segmentation • Import your own audio • Reference-to-Video - use 1-3 reference videos for character/object consistency
0:15

🚀 Wan 2.6 is now live on fal ! • Text-to-Video & Image-to-Video up to 1080p • Up to 15 second generations • Multi-shot video with intelligent scene segmentation • Import your own audio • Reference-to-Video - use 1-3 reference videos for character/object consistency

fal

64,542 views • 6 months ago

Matrix-Game 2.0 — The FIRST open-source, real-time, long-sequence interactive world model Last week, DeepMind's Genie 3 shook the AI world with real-time interactive world models. But... it wasn't open-sourced. Today, Matrix-Game 2.0 changed the game. 🚀 25FPS. Minutes-long interaction. Fully open-source.
0:10

Matrix-Game 2.0 — The FIRST open-source, real-time, long-sequence interactive world model Last week, DeepMind's Genie 3 shook the AI world with real-time interactive world models. But... it wasn't open-sourced. Today, Matrix-Game 2.0 changed the game. 🚀 25FPS. Minutes-long interaction. Fully open-source.

Skywork

1,398,728 views • 10 months ago

Gemini 3.1 Pro is now available for all paid tiers! The default model router, Auto (Gemini 3) will use Gemini 3.1 Pro as it's pro model for complex prompts. You can also set the new model via /model to try it out. We are excited to see how you put it to use!
0:12

Gemini 3.1 Pro is now available for all paid tiers! The default model router, Auto (Gemini 3) will use Gemini 3.1 Pro as it's pro model for complex prompts. You can also set the new model via /model to try it out. We are excited to see how you put it to use!

Gemini CLI

399,599 views • 4 months ago

Today we’re releasing Code Llama, a large language model built on top of Llama 2, fine-tuned for coding & state-of-the-art for publicly available coding tools. Keeping with our open approach, Code Llama is publicly-available now for both research & commercial use. More ⬇️
0:14

Today we’re releasing Code Llama, a large language model built on top of Llama 2, fine-tuned for coding & state-of-the-art for publicly available coding tools. Keeping with our open approach, Code Llama is publicly-available now for both research & commercial use. More ⬇️

AI at Meta

1,004,879 views • 2 years ago