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.

New AI research from Meta – CoTracker3 Simpler and Better Point Tracking by Pseudo-Labelling Real Videos. More details ➡️ Demo on Hugging Face ➡️ Building on our previous work on CoTracker, this new model demonstrates impressive tracking results where points can be tracked for a long time even when... show more

AI at Meta

879,463 subscribers

219,175 views • 2 years ago •via X (Twitter)

Science & Technology

Anya Rossi• Live Now

Private livecam show

10 Comments

jmpy2 years ago

@huggingface

BensenHsu2 years ago

The paper introduces a new point tracking model called CoTracker3 that builds upon recent point tracking models like PIPs, TAPIR, and CoTracker. Point tracking is an important task in video analysis for applications like 3D reconstruction and video editing. The CoTracker3 model, when trained only on synthetic data, already outperforms state-of-the-art trackers on several benchmarks. When further fine-tuned on just 15,000 real-world unlabeled videos using the proposed protocol, it significantly surpasses the performance of BootsTAPIR, which was trained on 15 million real videos. CoTracker3 also shows better handling of occluded points compared to other models. full paper:

Yufan Zhuang2 years ago

@huggingface love how meta keeps open-sourcing these research

Moses and AI2 years ago

@huggingface Your things @Mbounge_

Yosi Frost2 years ago

@huggingface That’s awesome!

Alex Fridd2 years ago

@huggingface Exciting development! Meta's new CoTracker3 could revolutionize point tracking in real videos.

AI_TechnoKing2 years ago

@huggingface This is wild.

GPT.Biz2 years ago

@huggingface This new AI model from Meta sounds impressive! CoTracker3 could really push forward developments in point tracking technology

Bhack2 years ago

@huggingface When are you going to release co-tracker under an Open Source/OSI license? It is the 3rd release under Creative Commons.

Phil Gjørup2 years ago

@huggingface wow!

Related Videos

We previously shared our research on Layer Skip, an end-to-end solution for accelerating LLMs from researchers at Meta FAIR. It achieves this by executing a subset of an LLM’s layers and utilizing subsequent layers for verification and correction. We’re now releasing inference code and fine-tuned checkpoints for this work. Model weights on Hugging Face ➡️ More details ➡️ We hope that releasing this work will open up new areas of experimentation and innovative new research in optimization and interpretability.

We previously shared our research on Layer Skip, an end-to-end solution for accelerating LLMs from researchers at Meta FAIR. It achieves this by executing a subset of an LLM’s layers and utilizing subsequent layers for verification and correction. We’re now releasing inference code and fine-tuned checkpoints for this work. Model weights on Hugging Face ➡️ More details ➡️ We hope that releasing this work will open up new areas of experimentation and innovative new research in optimization and interpretability.

AI at Meta

156,638 views • 2 years ago

Last week we released Meta Chameleon: a new mixed-modal research model from Meta FAIR. Get the models ➡️ The 7B & 34B safety tuned models we’ve released can take any combination of text and images as input and produce text outputs using a new early fusion approach. While some LLMs have separate image and text encoders or decoders, Chameleon is one of the first publicly released approaches using a single unified architecture. We’re releasing Chameleon models under a research license to help democratize access to foundational mixed-modal models & further research on early fusion. Approach & training details in the paper ➡️

Last week we released Meta Chameleon: a new mixed-modal research model from Meta FAIR. Get the models ➡️ The 7B & 34B safety tuned models we’ve released can take any combination of text and images as input and produce text outputs using a new early fusion approach. While some LLMs have separate image and text encoders or decoders, Chameleon is one of the first publicly released approaches using a single unified architecture. We’re releasing Chameleon models under a research license to help democratize access to foundational mixed-modal models & further research on early fusion. Approach & training details in the paper ➡️

AI at Meta

54,428 views • 2 years ago

New on Hugging Face — CoTracker simultaneously tracks the movement of multiple points in videos using a flexible design based on a transformer network — it models correlation of the points in time via specialized attention layers. 🤗 Try CoTracker ➡️

New on Hugging Face — CoTracker simultaneously tracks the movement of multiple points in videos using a flexible design based on a transformer network — it models correlation of the points in time via specialized attention layers. 🤗 Try CoTracker ➡️

AI at Meta

371,784 views • 3 years ago

We release a new urban simulator, MetaUrban, to support research on AI agents for micromobility. The work will be presented at #ICLR2025, and the demo code can run on any laptop. Webpage: Code: Paper:

We release a new urban simulator, MetaUrban, to support research on AI agents for micromobility. The work will be presented at #ICLR2025, and the demo code can run on any laptop. Webpage: Code: Paper:

Bolei Zhou

30,344 views • 1 year ago

Today we're sharing the next milestone in our Seamless Communication research — a new family of AI translation models that preserve expression and deliver near-real time streaming translations. More on this new work ➡️ More on the individual models 🧵

Today we're sharing the next milestone in our Seamless Communication research — a new family of AI translation models that preserve expression and deliver near-real time streaming translations. More on this new work ➡️ More on the individual models 🧵

AI at Meta

729,006 views • 2 years ago

New from Meta FAIR: Code World Model (CWM), a 32B-parameter research model designed to explore how world models can transform code generation and reasoning about code. We believe in advancing research in world modeling and are sharing CWM under a research license to help empower the community to build upon our work. ➡️ Read the technical report: ➡️Download the open weights: ➡️Download the code:

New from Meta FAIR: Code World Model (CWM), a 32B-parameter research model designed to explore how world models can transform code generation and reasoning about code. We believe in advancing research in world modeling and are sharing CWM under a research license to help empower the community to build upon our work. ➡️ Read the technical report: ➡️Download the open weights: ➡️Download the code:

AI at Meta

314,516 views • 1 year ago

SeamlessStreaming is an AI translation model that can deliver state-of-the-art results on streaming translation with <2 seconds of latency. One core piece of our latest Seamless Communication research work by teams at FAIR. More on this project ➡️

SeamlessStreaming is an AI translation model that can deliver state-of-the-art results on streaming translation with <2 seconds of latency. One core piece of our latest Seamless Communication research work by teams at FAIR. More on this project ➡️

AI at Meta

472,731 views • 2 years ago

We’ll also be showcasing a handful of demos on the showfloor. We brought Spotty to demo some of our exciting recent work towards general-purpose embodied AI agents. More on this research ➡️ 5/6

We’ll also be showcasing a handful of demos on the showfloor. We brought Spotty to demo some of our exciting recent work towards general-purpose embodied AI agents. More on this research ➡️ 5/6

AI at Meta

56,526 views • 3 years ago

Introducing Adjoint Sampling, a new learning algorithm that trains generative models based on scalar rewards. Based on theoretical foundations developed by FAIR, Adjoint Sampling leads to a highly scalable practical algorithm, and can become the foundation for further research into highly scalable sampling methods. Read our research paper on Adjoint Sampling and download the model, code, and benchmark ➡️

Introducing Adjoint Sampling, a new learning algorithm that trains generative models based on scalar rewards. Based on theoretical foundations developed by FAIR, Adjoint Sampling leads to a highly scalable practical algorithm, and can become the foundation for further research into highly scalable sampling methods. Read our research paper on Adjoint Sampling and download the model, code, and benchmark ➡️

AI at Meta

36,987 views • 1 year ago

A new paper by Disney Research introduces a 2-stage technique for motion tracking in physics-based character animation, using a pretrained latent space and RL to control diverse and unseen motions on both virtual and real-world humanoid robots. Paper:

A new paper by Disney Research introduces a 2-stage technique for motion tracking in physics-based character animation, using a pretrained latent space and RL to control diverse and unseen motions on both virtual and real-world humanoid robots. Paper:

The Humanoid Hub

20,117 views • 2 years ago

Can 1,000 real-world 3D scenes make a state-of-the-art model better? At OVER Research, we tested it by fine-tuning R3, a state-of-the-art streaming 3D reconstruction model, on roughly 1,000 scenes from the OVER dataset. The result: 25% lower trajectory error on our real-world environments compared to the deployed public checkpoint. And we did it using only 1,000 scenes, the same open dataset anyone can download for free, out of the 285,000+ real-world 3D scenes OVER has today. Read the full OVER Research publication: Download the 1,000-scene dataset on Hugging Face:

Can 1,000 real-world 3D scenes make a state-of-the-art model better? At OVER Research, we tested it by fine-tuning R3, a state-of-the-art streaming 3D reconstruction model, on roughly 1,000 scenes from the OVER dataset. The result: 25% lower trajectory error on our real-world environments compared to the deployed public checkpoint. And we did it using only 1,000 scenes, the same open dataset anyone can download for free, out of the 285,000+ real-world 3D scenes OVER has today. Read the full OVER Research publication: Download the 1,000-scene dataset on Hugging Face:

Over the Reality 🌐

34,785 views • 2 months ago

Introducing Falcon Mamba 7B from TII! This state-of-the-art language model sets a new AI benchmark with its innovative state space architecture. This groundbreaking release marks a significant stride in AI research. Learn more on

Introducing Falcon Mamba 7B from TII! This state-of-the-art language model sets a new AI benchmark with its innovative state space architecture. This groundbreaking release marks a significant stride in AI research. Learn more on

Technology Innovation Institute

29,833 views • 2 years ago

PointOdyssey: A Large-Scale Synthetic Dataset for Long-Term Point Tracking paper page: introduce PointOdyssey, a large-scale synthetic dataset, and data generation framework, for the training and evaluation of long-term fine-grained tracking algorithms. Our goal is to advance the state-of-the-art by placing emphasis on long videos with naturalistic motion. Toward the goal of naturalism, we animate deformable characters using real-world motion capture data, we build 3D scenes to match the motion capture environments, and we render camera viewpoints using trajectories mined via structure-from-motion on real videos. We create combinatorial diversity by randomizing character appearance, motion profiles, materials, lighting, 3D assets, and atmospheric effects. Our dataset currently includes 104 videos, averaging 2,000 frames long, with orders of magnitude more correspondence annotations than prior work. We show that existing methods can be trained from scratch in our dataset and outperform the published variants. Finally, we introduce modifications to the PIPs point tracking method, greatly widening its temporal receptive field, which improves its performance on PointOdyssey as well as on two real-world benchmarks.

PointOdyssey: A Large-Scale Synthetic Dataset for Long-Term Point Tracking paper page: introduce PointOdyssey, a large-scale synthetic dataset, and data generation framework, for the training and evaluation of long-term fine-grained tracking algorithms. Our goal is to advance the state-of-the-art by placing emphasis on long videos with naturalistic motion. Toward the goal of naturalism, we animate deformable characters using real-world motion capture data, we build 3D scenes to match the motion capture environments, and we render camera viewpoints using trajectories mined via structure-from-motion on real videos. We create combinatorial diversity by randomizing character appearance, motion profiles, materials, lighting, 3D assets, and atmospheric effects. Our dataset currently includes 104 videos, averaging 2,000 frames long, with orders of magnitude more correspondence annotations than prior work. We show that existing methods can be trained from scratch in our dataset and outperform the published variants. Finally, we introduce modifications to the PIPs point tracking method, greatly widening its temporal receptive field, which improves its performance on PointOdyssey as well as on two real-world benchmarks.

AK

122,567 views • 3 years ago

I'm thrilled to announce the launch of ⚡️Flash Diffusion from Jasper! Earlier this year, with our acquisition of Clipdrop, we launched the Jasper AI Research Lab in Paris. Today, we are excited to release our first piece of groundbreaking research: the open-source distillation method, "Flash Diffusion". Flash Diffusion accelerates inference by 500%, reduces computing costs, and produces higher-quality image outputs. Dive into the details and discover how Flash Diffusion is set to revolutionize the field of AI and image synthesis. Read all about it here: Try a demo on Hugging Face:

I'm thrilled to announce the launch of ⚡️Flash Diffusion from Jasper! Earlier this year, with our acquisition of Clipdrop, we launched the Jasper AI Research Lab in Paris. Today, we are excited to release our first piece of groundbreaking research: the open-source distillation method, "Flash Diffusion". Flash Diffusion accelerates inference by 500%, reduces computing costs, and produces higher-quality image outputs. Dive into the details and discover how Flash Diffusion is set to revolutionize the field of AI and image synthesis. Read all about it here: Try a demo on Hugging Face:

Timothy Young

10,180 views • 2 years ago

We made a @gradio demo for AllTracker! AllTracker is the current state-of-the-art for general-purpose point tracking. The demo gives a good sense of the accuracy---try your own videos and see for yourself! 🔗 Demo: 💻 Code:

We made a @gradio demo for AllTracker! AllTracker is the current state-of-the-art for general-purpose point tracking. The demo gives a good sense of the accuracy---try your own videos and see for yourself! 🔗 Demo: 💻 Code:

Adam W. Harley

41,631 views • 1 year ago

every other day i yearn for more research fields to adopt the culture from the ML and ML adjacent fields of building a demo website for each paper and put code on github

every other day i yearn for more research fields to adopt the culture from the ML and ML adjacent fields of building a demo website for each paper and put code on github

outside five sigma

27,415 views • 1 year ago

Open science is how we continue to push technology forward and today at Meta FAIR we’re sharing eight new AI research artifacts including new models, datasets and code to inspire innovation in the community. More in the video from @jpineau1. This work is another important step towards our goal of achieving Advanced Machine Intelligence (AMI). What we’re releasing: • Meta Spirit LM: An open source language model for seamless speech and text integration. • Meta Segment Anything Model 2.1: An updated checkpoint with improved results on visually similar objects, small objects and occlusion handling. Plus a new developer suite to make it easier for developers to build with SAM 2. • Layer Skip: Inference code and fine-tuned checkpoints demonstrating a new method for enhancing LLM performance. • SALSA: New code to enable researchers to benchmark AI-based attacks in support of validating security for post-quantum cryptography. • Meta Lingua: A lightweight and self-contained codebase designed to train language models at scale. • Meta Open Materials: New open source models and the largest dataset of its kind to accelerate AI-driven discovery of new inorganic materials. • MEXMA: A new research paper and code for our novel pre-trained cross-lingual sentence encoder with coverage across 80 languages. • Self-Taught Evaluator: a new method for generating synthetic preference data to train reward models without relying on human annotations. Access to state-of-the-art AI creates opportunities for everyone. We’re excited to share this work and look forward to seeing the community innovation that results from it. Details and access to everything released by FAIR today ➡️

Open science is how we continue to push technology forward and today at Meta FAIR we’re sharing eight new AI research artifacts including new models, datasets and code to inspire innovation in the community. More in the video from @jpineau1. This work is another important step towards our goal of achieving Advanced Machine Intelligence (AMI). What we’re releasing: • Meta Spirit LM: An open source language model for seamless speech and text integration. • Meta Segment Anything Model 2.1: An updated checkpoint with improved results on visually similar objects, small objects and occlusion handling. Plus a new developer suite to make it easier for developers to build with SAM 2. • Layer Skip: Inference code and fine-tuned checkpoints demonstrating a new method for enhancing LLM performance. • SALSA: New code to enable researchers to benchmark AI-based attacks in support of validating security for post-quantum cryptography. • Meta Lingua: A lightweight and self-contained codebase designed to train language models at scale. • Meta Open Materials: New open source models and the largest dataset of its kind to accelerate AI-driven discovery of new inorganic materials. • MEXMA: A new research paper and code for our novel pre-trained cross-lingual sentence encoder with coverage across 80 languages. • Self-Taught Evaluator: a new method for generating synthetic preference data to train reward models without relying on human annotations. Access to state-of-the-art AI creates opportunities for everyone. We’re excited to share this work and look forward to seeing the community innovation that results from it. Details and access to everything released by FAIR today ➡️

AI at Meta

150,632 views • 2 years ago

New LLMs that control UIs! ByteDance Research releases UI-TARS, fine-tuned GUI agent that integrates reasoning, and action capabilities into a single vision-language model. Think of computer use but open. 👀 TL;DR; 3️⃣ Available in 3 sizes: 2B, 7B, and 72B parameters 🧠 Trained Qwen2-VL models with SFT & DPO 🥇 72B version achieves 82.8% on VisualWebBench (beating GPT-4 and Claude) 🏆 Achieves state-of-the-art results on 10+ GUI agent benchmarks 💡 Reasons before taking an action 🧑🏻‍💻 Can Click, Long Press, type, scroll, open app, navigate back/home, wait 🤗 Released under Apache 2.0 on Hugging Face

New LLMs that control UIs! ByteDance Research releases UI-TARS, fine-tuned GUI agent that integrates reasoning, and action capabilities into a single vision-language model. Think of computer use but open. 👀 TL;DR; 3️⃣ Available in 3 sizes: 2B, 7B, and 72B parameters 🧠 Trained Qwen2-VL models with SFT & DPO 🥇 72B version achieves 82.8% on VisualWebBench (beating GPT-4 and Claude) 🏆 Achieves state-of-the-art results on 10+ GUI agent benchmarks 💡 Reasons before taking an action 🧑🏻‍💻 Can Click, Long Press, type, scroll, open app, navigate back/home, wait 🤗 Released under Apache 2.0 on Hugging Face

Philipp Schmid

48,170 views • 1 year ago