Loading video...

Video Failed to Load

Go Home

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!

VectorWang2's profile picture

Vector Wang

2,228 subscribers

22,583 views • 8 months ago •via X (Twitter)

LIVE

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
0:21

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 • 7 months ago

Stereo depth models usually force a tradeoff. 📌 Paper + Code Either strong zero-shot generalization or real-time speed. Fast-FoundationStereo closes that gap. The model accelerates FoundationStereo by more than 10× while keeping comparable depth quality, making real-time stereo matching practical for robotics and XR. On an RTX 3090, it produces dense metric depth maps and 3D point clouds in real time, outperforming existing real-time stereo approaches and even challenging some heavier zero-shot models. The key idea is a divide-and-conquer architecture that removes bottlenecks in common stereo matching components while preserving the strengths of the original teacher model. Training also tackles a major constraint in stereo vision: the lack of ground-truth metric depth data. The team built an automatic data curation pipeline that generates pseudo-labels from internet-scale stereo imagery using the Stereo4D dataset. Result: a real-time stereo foundation model with strong zero-shot performance and practical runtime speed. Code, pretrained weights, and pseudo-labeled stereo data will be released. Thanks for sharing, Bowen Wen! 📍Paper: Code: Project: ——- Weekly robotics and AI insights. Subscribe free:
0:25

Stereo depth models usually force a tradeoff. 📌 Paper + Code Either strong zero-shot generalization or real-time speed. Fast-FoundationStereo closes that gap. The model accelerates FoundationStereo by more than 10× while keeping comparable depth quality, making real-time stereo matching practical for robotics and XR. On an RTX 3090, it produces dense metric depth maps and 3D point clouds in real time, outperforming existing real-time stereo approaches and even challenging some heavier zero-shot models. The key idea is a divide-and-conquer architecture that removes bottlenecks in common stereo matching components while preserving the strengths of the original teacher model. Training also tackles a major constraint in stereo vision: the lack of ground-truth metric depth data. The team built an automatic data curation pipeline that generates pseudo-labels from internet-scale stereo imagery using the Stereo4D dataset. Result: a real-time stereo foundation model with strong zero-shot performance and practical runtime speed. Code, pretrained weights, and pseudo-labeled stereo data will be released. Thanks for sharing, Bowen Wen! 📍Paper: Code: Project: ——- Weekly robotics and AI insights. Subscribe free:

Ilir Aliu

11,914 views • 2 months ago

"Fast Foundation Stereo: When Foundation Models Meet Efficient Stereo Matching" TL;DR: distills stereo foundation models into an efficient real-time stereo matching framework, preserving high accuracy while dramatically reducing inference cost.
0:47

"Fast Foundation Stereo: When Foundation Models Meet Efficient Stereo Matching" TL;DR: distills stereo foundation models into an efficient real-time stereo matching framework, preserving high accuracy while dramatically reducing inference cost.

Alexandre Morgand

14,854 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 ➡️
0:51

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.
0:22

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

290,412 views • 3 years ago

Zero V2 finally in my hands - Way sharper display - Around 38° FOV - 20x faster thanks to CM4 - Dual integrated batteries - 160° Camera - Stereo speakers - Proper stereo displays The design seems to work, now I'll clean it up a bit, then do a lot of software-writing. #xr #ar
0:31

Zero V2 finally in my hands - Way sharper display - Around 38° FOV - 20x faster thanks to CM4 - Dual integrated batteries - 160° Camera - Stereo speakers - Proper stereo displays The design seems to work, now I'll clean it up a bit, then do a lot of software-writing. #xr #ar

Miroslav Kotalík

54,941 views • 1 year ago

A new milestone for real-time accurate 3D spatial computing! Introducing ⚡️Fast-FoundationStereo⚡️, a real-time zero-shot stereo depth estimation model that accelerates the original FoundationStereo by >10x with comparable quality. Details in threads 🧵 (1/N)
0:30

A new milestone for real-time accurate 3D spatial computing! Introducing ⚡️Fast-FoundationStereo⚡️, a real-time zero-shot stereo depth estimation model that accelerates the original FoundationStereo by >10x with comparable quality. Details in threads 🧵 (1/N)

Bowen Wen

77,328 views • 10 months ago

CosmicMan A Text-to-Image Foundation Model for Humans We present CosmicMan, a text-to-image foundation model specialized for generating high-fidelity human images. Unlike current general-purpose foundation models that are stuck in the dilemma of inferior quality and
0:50

CosmicMan A Text-to-Image Foundation Model for Humans We present CosmicMan, a text-to-image foundation model specialized for generating high-fidelity human images. Unlike current general-purpose foundation models that are stuck in the dilemma of inferior quality and

AK

46,778 views • 2 years ago

zero-shot image segmentation with Florence-2 + SAM-2 combo just added new mode to my Hugging Face; now you can run open vocabulary detection with Florence-2 + box to mask with SAM2 link:
0:26

zero-shot image segmentation with Florence-2 + SAM-2 combo just added new mode to my Hugging Face; now you can run open vocabulary detection with Florence-2 + box to mask with SAM2 link:

SkalskiP

66,083 views • 2 years ago

Florence-2, the new vision foundation model by Microsoft, can now run 100% locally in your browser on WebGPU, thanks to Transformers.js! 🤗🤯 It supports tasks like image captioning, optical character recognition, object detection, and many more! 😍 WOW! Demo (+ source code) 👇
1:05

Florence-2, the new vision foundation model by Microsoft, can now run 100% locally in your browser on WebGPU, thanks to Transformers.js! 🤗🤯 It supports tasks like image captioning, optical character recognition, object detection, and many more! 😍 WOW! Demo (+ source code) 👇

Xenova

88,782 views • 2 years ago

stereo depth map on the orange pi is now at 18-22.4 FPS all of the compute is happening on the orange pi zero, including camera capture. it is the board on the bottom with a quarter for scale.
0:59

stereo depth map on the orange pi is now at 18-22.4 FPS all of the compute is happening on the orange pi zero, including camera capture. it is the board on the bottom with a quarter for scale.

kache

17,792 views • 2 months ago

13yr-old Hamza went with his uncle to a US aid point run by the Gaza Humanitarian Foundation – they shot him in the head #FiringSquads
0:42

13yr-old Hamza went with his uncle to a US aid point run by the Gaza Humanitarian Foundation – they shot him in the head #FiringSquads

Sarah Wilkinson

12,851 views • 1 year ago

Boston Dynamics collaborated with NVIDIA to demonstrate DextrAH-RGB, a workflow for dexterous grasping from stereo RGB input. The end-to-end policy for Atlas robot, trained entirely in NVIDIA Isaac Lab, transfers zero-shot from simulation to the real robot.
2:01

Boston Dynamics collaborated with NVIDIA to demonstrate DextrAH-RGB, a workflow for dexterous grasping from stereo RGB input. The end-to-end policy for Atlas robot, trained entirely in NVIDIA Isaac Lab, transfers zero-shot from simulation to the real robot.

The Humanoid Hub

79,781 views • 1 year ago

Thanks to CC Sabathia, Amber Sabathia, PitCCh In Foundation, and all the celebrities for putting on a great show at last night's Celebrity Softball Game! Funds and proceeds raised through the event benefited the PitCCh In Foundation & the New York Yankees Foundation.
2:15

Thanks to CC Sabathia, Amber Sabathia, PitCCh In Foundation, and all the celebrities for putting on a great show at last night's Celebrity Softball Game! Funds and proceeds raised through the event benefited the PitCCh In Foundation & the New York Yankees Foundation.

New York Yankees

162,099 views • 3 years ago

A gigantic #UFO Wheel was filmed by the STEREO-A satellite for several days in 2020, the object appears to be deploying a sort of shield #uap #ovni
1:16

A gigantic #UFO Wheel was filmed by the STEREO-A satellite for several days in 2020, the object appears to be deploying a sort of shield #uap #ovni

Jenined🔻UFO Research

314,062 views • 1 year ago

HD, NO CREDITS, NO STUPID MASKING, PEAK FICTION THAT IS LISTEN TO THE STEREO OFFICIALLY FOR FREE YEAAAAAHHHHHHHHHHHHHHHHHHH
1:29

HD, NO CREDITS, NO STUPID MASKING, PEAK FICTION THAT IS LISTEN TO THE STEREO OFFICIALLY FOR FREE YEAAAAAHHHHHHHHHHHHHHHHHHH

ULLLTIMMAAAAA🍉🇵🇸

30,964 views • 1 month ago

MAC-VO: Metrics-Aware Covariance for Learning-based Stereo Visual Odometry TL;DR: learning-based stereo; learned metrics-aware matching uncertainty for dual purposes: selecting keypoint and weighing the residual in pose graph optimization.
0:35

MAC-VO: Metrics-Aware Covariance for Learning-based Stereo Visual Odometry TL;DR: learning-based stereo; learned metrics-aware matching uncertainty for dual purposes: selecting keypoint and weighing the residual in pose graph optimization.

Alexandre Morgand

17,367 views • 1 year ago

Treat the Phil Collins fan in your life with the new 2025 Dolby Atmos mix of "No Jacket Required” on Blu-ray Audio disc. Featuring new stereo, 5.1 and Dolby Atmos mixes of "No Jacket Required" by Steven Wilson, plus the original 1985 stereo mix. Order:
0:34

Treat the Phil Collins fan in your life with the new 2025 Dolby Atmos mix of "No Jacket Required” on Blu-ray Audio disc. Featuring new stereo, 5.1 and Dolby Atmos mixes of "No Jacket Required" by Steven Wilson, plus the original 1985 stereo mix. Order:

Phil Collins

12,628 views • 11 months ago