Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

Fast Foundation Stereo + SAM2 basically = zero shot Foundation Pose😂 No CAD model, no object image, just click the target. Run directly on my 3070 at 13fps, with a 30$ stereo camera (calibrated in 10min) Thanks Bowen Wen for his contribution to the community!

Vector Wang

2,093 subscribers

22,496 views • 4 months ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Why can't “world models” just be sim? A real-time real2sim demo in the upcoming “ManiDreams” Foundation Stereo + SAM2 + Newton = Generalizable 3D physics prediction in a fast (15FPS) and lightweight (3070) way. No data or object mesh needed

Why can't “world models” just be sim? A real-time real2sim demo in the upcoming “ManiDreams” Foundation Stereo + SAM2 + Newton = Generalizable 3D physics prediction in a fast (15FPS) and lightweight (3070) way. No data or object mesh needed

Vector Wang

30,474 views • 3 months ago

The Segment Anything Model (SAM) by Meta AI is a step toward the first foundation model for image segmentation. SAM is capable of one-click segmentation of any object from photos or videos + zero-shot transfer to other segmentation tasks. Try the demo ➡️

The Segment Anything Model (SAM) by Meta AI is a step toward the first foundation model for image segmentation. SAM is capable of one-click segmentation of any object from photos or videos + zero-shot transfer to other segmentation tasks. Try the demo ➡️

AI at Meta

186,348 views • 3 years ago

Big News! Meta just released Segment Anything, a new AI model that can "cut out" any object, in any image/video, with a single click. The model is designed and trained to be promptable, so it can transfer zero-shot to new image distributions and tasks.

Big News! Meta just released Segment Anything, a new AI model that can "cut out" any object, in any image/video, with a single click. The model is designed and trained to be promptable, so it can transfer zero-shot to new image distributions and tasks.

Lior Alexander

290,190 views • 3 years ago

hi all, excited to join! i'm building an expressive mini "shoggoth" robot which will eventually be hooked up to gpt4o realtime voice. i'm currently working on the low-level policies, which are trained in a mujoco simulation with RL. to delay working on raw-pixels for now, i trained a pose-estimation model using deeplabcut and triangulate the position in 3d space using the stereo cameras. eventually, i'll use gpt4o's tool calling capabilities to activate several of these policies (closed and open loop) based on the dialog flow! captions: manual actuation of the tentacle / 3d pose estimation / target design

hi all, excited to join! i'm building an expressive mini "shoggoth" robot which will eventually be hooked up to gpt4o realtime voice. i'm currently working on the low-level policies, which are trained in a mujoco simulation with RL. to delay working on raw-pixels for now, i trained a pose-estimation model using deeplabcut and triangulate the position in 3d space using the stereo cameras. eventually, i'll use gpt4o's tool calling capabilities to activate several of these policies (closed and open loop) based on the dialog flow! captions: manual actuation of the tentacle / 3d pose estimation / target design

Matthieu LC

45,506 views • 1 year ago

RIGHT NOW: Looking forward to anchoring my first Sunday night Sports Xtra on CBS Chicago. Check out my Q&A with #Bears rookie QB Caleb Williams Caleb Williams who’s already throwing touchdowns in the community at his 1st Caleb Cares Foundation event on the #SouthSide of #Chicago.

RIGHT NOW: Looking forward to anchoring my first Sunday night Sports Xtra on CBS Chicago. Check out my Q&A with #Bears rookie QB Caleb Williams Caleb Williams who’s already throwing touchdowns in the community at his 1st Caleb Cares Foundation event on the #SouthSide of #Chicago.

Ryan Baker

34,554 views • 2 years 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

🚀 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

178,481 views • 1 year ago

Mookie Betts hosted his second annual pickleball tournament for his 50/50 Foundation today. “Anything with a ball, I try and get good at. When I got here, I started loving it and found a community. With my charity, I wanted to tie the two in.” 🙌

Mookie Betts hosted his second annual pickleball tournament for his 50/50 Foundation today. “Anything with a ball, I try and get good at. When I got here, I started loving it and found a community. With my charity, I wanted to tie the two in.” 🙌

Dodgers Nation

26,095 views • 27 days ago

NVIDIA just unleashed SANA-WM and it’s an absolute MONSTER for the future of open source AI! A blazing-fast 2.6B-parameter open-source world model that doesn’t just generate video… it creates controllable, physics-rich, high-fidelity worlds on demand. Why this is insanely powerful: • One image + text prompt + 6-DoF camera trajectory → generates 720p videos up to 60 seconds long with buttery-smooth, precisely controlled camera movement. You’re not just watching, you’re piloting the simulation. • Runs locally on a single consumer GPU (RTX 5090 level) thanks to heavy distillation + NVFP4 quantization. Full 60-second clip denoised in ~34 seconds. No massive clusters required. • 36× higher throughput than previous open models while rivaling (or beating) closed industrial giants in visual quality and consistency. • Trained lightning-fast: ~213K public videos in just 15 days on 64 H100s. • Built with next-level tech: Hybrid Linear Attention, dual-branch camera control, two-stage pipeline, and rock-solid metric-scale pose understanding. This is a true open world model, the foundation for embodied AI, robotics, autonomous systems, and hyper-realistic simulations that can run anywhere. Project: At our Zero-Human Company, we’re already running SANA-WM live in our core pipelines. It’s supercharging autonomous agent training, generating unlimited synthetic training data, and powering full end-to-end simulation loops, zero humans in the loop. The speed and control let us test thousands of edge-case scenarios overnight, iterate at lightspeed, and push our fully autonomous operations further than ever before. This is the kind of breakthrough that turns science fiction into daily reality. World models just leveled up — hard. The age of personal, local, controllable universes is here.

NVIDIA just unleashed SANA-WM and it’s an absolute MONSTER for the future of open source AI! A blazing-fast 2.6B-parameter open-source world model that doesn’t just generate video… it creates controllable, physics-rich, high-fidelity worlds on demand. Why this is insanely powerful: • One image + text prompt + 6-DoF camera trajectory → generates 720p videos up to 60 seconds long with buttery-smooth, precisely controlled camera movement. You’re not just watching, you’re piloting the simulation. • Runs locally on a single consumer GPU (RTX 5090 level) thanks to heavy distillation + NVFP4 quantization. Full 60-second clip denoised in ~34 seconds. No massive clusters required. • 36× higher throughput than previous open models while rivaling (or beating) closed industrial giants in visual quality and consistency. • Trained lightning-fast: ~213K public videos in just 15 days on 64 H100s. • Built with next-level tech: Hybrid Linear Attention, dual-branch camera control, two-stage pipeline, and rock-solid metric-scale pose understanding. This is a true open world model, the foundation for embodied AI, robotics, autonomous systems, and hyper-realistic simulations that can run anywhere. Project: At our Zero-Human Company, we’re already running SANA-WM live in our core pipelines. It’s supercharging autonomous agent training, generating unlimited synthetic training data, and powering full end-to-end simulation loops, zero humans in the loop. The speed and control let us test thousands of edge-case scenarios overnight, iterate at lightspeed, and push our fully autonomous operations further than ever before. This is the kind of breakthrough that turns science fiction into daily reality. World models just leveled up — hard. The age of personal, local, controllable universes is here.

Brian Roemmele

618,220 views • 2 months ago

🏦 Institutional RWA Vaults Just Launched On XDC Network Raze Finance joins XDC Foundation and Plug & Play to showcase infrastructure for the next $1T in RWA yield. Private credit. Commodities. Structured debt. All accessible with USDC. Deploy stablecoins. Earn from real world assets. Native settlement. No protocol token loops. Vault infrastructure handles custody, compliance, and distribution automatically. Built for stablecoin holders that are ready to move beyond zero yield. Raze XDC Foundation Plug and Play Tech Center Podcast supported by the XDC Foundation

🏦 Institutional RWA Vaults Just Launched On XDC Network Raze Finance joins XDC Foundation and Plug & Play to showcase infrastructure for the next $1T in RWA yield. Private credit. Commodities. Structured debt. All accessible with USDC. Deploy stablecoins. Earn from real world assets. Native settlement. No protocol token loops. Vault infrastructure handles custody, compliance, and distribution automatically. Built for stablecoin holders that are ready to move beyond zero yield. Raze XDC Foundation Plug and Play Tech Center Podcast supported by the XDC Foundation

Generation Infinity

72,476 views • 5 months ago

There’s something special about hearing Bob Moog explain synthesis in his own words on the instrument that opened the door for generations of music makers to come. 💡 Sharing this little piece of history today as we celebrate Bob’s legacy and visionary spirit with the new Bob Moog Tribute Edition Minimoog Model D—a portion of each unit sold will be donated directly to the Bob Moog Foundation, supporting the Moogseum, Dr. Bob’s Sound School, and the preservation of the Bob Moog Foundation Archives. Learn more at #Moog #Minimoog #BobMoog #synthhistory

There’s something special about hearing Bob Moog explain synthesis in his own words on the instrument that opened the door for generations of music makers to come. 💡 Sharing this little piece of history today as we celebrate Bob’s legacy and visionary spirit with the new Bob Moog Tribute Edition Minimoog Model D—a portion of each unit sold will be donated directly to the Bob Moog Foundation, supporting the Moogseum, Dr. Bob’s Sound School, and the preservation of the Bob Moog Foundation Archives. Learn more at #Moog #Minimoog #BobMoog #synthhistory

Moog Synthesizers

14,439 views • 3 months ago

Ryan Young painted my helmets for years and is well-respected in the motorsports community. Unfortunately, he passed earlier this year following his battle with cancer. In honor of Ryan and the legacy he built with IndocilArt, I’ve partnered with his son on a memorial helmet to be worn this weekend at Bristol Motor Speedway. This helmet is now up for auction on the Erik Jones Foundation site in support of the Young family. #earlydetectionsaveslives Bid here:

Ryan Young painted my helmets for years and is well-respected in the motorsports community. Unfortunately, he passed earlier this year following his battle with cancer. In honor of Ryan and the legacy he built with IndocilArt, I’ve partnered with his son on a memorial helmet to be worn this weekend at Bristol Motor Speedway. This helmet is now up for auction on the Erik Jones Foundation site in support of the Young family. #earlydetectionsaveslives Bid here:

Erik Jones

15,008 views • 1 year ago

After selling out a few days ago, Tesla has just uploaded a lot more used Cybertrucks on their inventory website, but with higher average pricing. Prices now start at $72,900 for a used 2024 Foundation Series Cybertruck with 32,845 miles (vs $66,200 a few days ago for a used 2024 Foundation Series with 2,566 miles). Prices currently peak at $96,100 for a used Cyberbeast Foundation Series with 14,927 miles. There are various Foundation and non-Foundation Series trucks available, including 2024 and 2025 model year trucks. These are different used trucks than the ones from a few days ago since the milage numbers are different. Tesla will transport one to any Tesla delivery location of your choice in the continental US for up to $2,500. Keep in mind the $2,500 delivery transportation fee is an estimate and will be confirmed once an order is placed. Link to used inventory in thread below:

After selling out a few days ago, Tesla has just uploaded a lot more used Cybertrucks on their inventory website, but with higher average pricing. Prices now start at $72,900 for a used 2024 Foundation Series Cybertruck with 32,845 miles (vs $66,200 a few days ago for a used 2024 Foundation Series with 2,566 miles). Prices currently peak at $96,100 for a used Cyberbeast Foundation Series with 14,927 miles. There are various Foundation and non-Foundation Series trucks available, including 2024 and 2025 model year trucks. These are different used trucks than the ones from a few days ago since the milage numbers are different. Tesla will transport one to any Tesla delivery location of your choice in the continental US for up to $2,500. Keep in mind the $2,500 delivery transportation fee is an estimate and will be confirmed once an order is placed. Link to used inventory in thread below:

Sawyer Merritt

459,449 views • 1 month ago

Wesley Snipes was so bad at baseball, that there’s no scene of him actually throwing a ball in Major League. He is slow too. When they did his run scene at training camp they told the two runners to jog basically to make him look fast. One laughed and said i was almost walking lol. Thus the reason the scene was shot in slow motion.

Wesley Snipes was so bad at baseball, that there’s no scene of him actually throwing a ball in Major League. He is slow too. When they did his run scene at training camp they told the two runners to jog basically to make him look fast. One laughed and said i was almost walking lol. Thus the reason the scene was shot in slow motion.

BaseballHistoryNut

4,078,160 views • 6 months ago

Wesley Snipes was so bad at baseball, that there’s no scene of him actually throwing a ball in Major League. He is slow too. When they did his run scene at training camp they told the two runners to jog basically to make him look fast. One laughed and said i was almost walking lol. Thus the reason the scene was shot in slow motion.

Wesley Snipes was so bad at baseball, that there’s no scene of him actually throwing a ball in Major League. He is slow too. When they did his run scene at training camp they told the two runners to jog basically to make him look fast. One laughed and said i was almost walking lol. Thus the reason the scene was shot in slow motion.

BaseballHistoryNut

1,401,973 views • 26 days ago

"You just wonder how long that runway's gonna be for Anthony with the way he's struggled at the plate now for an extended stretch." Ruocco and Cone discuss Anthony Volpe as his slump increases to 3-for-30 with no extra-base hits since his home run in Kansas City on May 26th

"You just wonder how long that runway's gonna be for Anthony with the way he's struggled at the plate now for an extended stretch." Ruocco and Cone discuss Anthony Volpe as his slump increases to 3-for-30 with no extra-base hits since his home run in Kansas City on May 26th

Talkin' Yanks

196,133 views • 1 month ago

Remember when life was this simple? No smartphones. No social media. No notifications every 30 seconds. Just cruising around town, grabbing Pizza Hut with friends, playing Nintendo until your parents told you to go to bed, and listening to music on whatever stereo happened to be in the living room. Sometimes it feels like we gained convenience and lost a little bit of everything else. If you could spend one week back in the 1980s, what would you do?

Remember when life was this simple? No smartphones. No social media. No notifications every 30 seconds. Just cruising around town, grabbing Pizza Hut with friends, playing Nintendo until your parents told you to go to bed, and listening to music on whatever stereo happened to be in the living room. Sometimes it feels like we gained convenience and lost a little bit of everything else. If you could spend one week back in the 1980s, what would you do?

fOx

18,851 views • 1 month ago

Kimmy K2.5 just launched a local cloud model. And it runs Open Claw for FREE forever. No API costs. No token limits. No subscriptions. Here's the setup 👇 → Download Ollama at → Install Kimmy K2.5 cloud model. → Launch Open Claw with one command. → Runs locally but uses cloud processing. → Zero laptop slowdown. → Works on older machines perfectly. I just set it up in under 2 minutes. Zero configuration. Zero technical skills. Want the commands? DM me.

Kimmy K2.5 just launched a local cloud model. And it runs Open Claw for FREE forever. No API costs. No token limits. No subscriptions. Here's the setup 👇 → Download Ollama at → Install Kimmy K2.5 cloud model. → Launch Open Claw with one command. → Runs locally but uses cloud processing. → Zero laptop slowdown. → Works on older machines perfectly. I just set it up in under 2 minutes. Zero configuration. Zero technical skills. Want the commands? DM me.

Julian Goldie SEO

240,087 views • 5 months ago

From Zero to One: The NodeOps Story In just two years, NodeOps has grown from a 3-person team into: → A protocol generating $4.4M+ in revenue → One of the leading DePIN projects → A community of 700K+ verified users → A network powering 23K+ deployments, 5K+ machines, and 1K+ providers Our mission is simple: make infrastructure invisible and empower builders to focus on what matters, their ideas. That’s why we built Autogen, a one-stop platform for deployment, scaling, and coordination. Autogen makes it seamless to go from idea to production with AI-powered deployment and zero downtime. NodeOps isn’t just infrastructure, it’s the foundation for the next wave of AI, data, and decentralized applications. At the core of it all is $NODE, with a dynamic burn/mint model directly tied to real network revenue. Watch Sheena break it all down 👇🏻

From Zero to One: The NodeOps Story In just two years, NodeOps has grown from a 3-person team into: → A protocol generating $4.4M+ in revenue → One of the leading DePIN projects → A community of 700K+ verified users → A network powering 23K+ deployments, 5K+ machines, and 1K+ providers Our mission is simple: make infrastructure invisible and empower builders to focus on what matters, their ideas. That’s why we built Autogen, a one-stop platform for deployment, scaling, and coordination. Autogen makes it seamless to go from idea to production with AI-powered deployment and zero downtime. NodeOps isn’t just infrastructure, it’s the foundation for the next wave of AI, data, and decentralized applications. At the core of it all is $NODE, with a dynamic burn/mint model directly tied to real network revenue. Watch Sheena break it all down 👇🏻

NodeOps

22,802 views • 9 months ago

I ask this with no exaggeration: Is this the greatest non-pro golf shot ever caught on camera? At the Concession no less, one of the hardest golf courses in the USA. This is why you go for the stupid shot. Screw analytics and data. You don’t become a hero by laying up. All hero shots start with some stupidity! Shot by Brad Kordel. Kordelicious is his IG account.

I ask this with no exaggeration: Is this the greatest non-pro golf shot ever caught on camera? At the Concession no less, one of the hardest golf courses in the USA. This is why you go for the stupid shot. Screw analytics and data. You don’t become a hero by laying up. All hero shots start with some stupidity! Shot by Brad Kordel. Kordelicious is his IG account.

Rick Golfs

549,368 views • 1 year ago