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.

Pixie Fast and Generalizable Supervised Learning of 3D Physics from Pixels

AK

438,868 subscribers

21,434 views • 10 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

Supervised learning has held 3D Vision back for too long. Meet RayZer — a self-supervised 3D model trained with zero 3D labels: ❌ No supervision of camera & geometry ✅ Just RGB images And the wild part? RayZer outperforms supervised methods (as 3D labels from COLMAP is noisy) 🌐 Project: (1/4)

Supervised learning has held 3D Vision back for too long. Meet RayZer — a self-supervised 3D model trained with zero 3D labels: ❌ No supervision of camera & geometry ✅ Just RGB images And the wild part? RayZer outperforms supervised methods (as 3D labels from COLMAP is noisy) 🌐 Project: (1/4)

Hanwen Jiang

69,607 views • 1 year ago

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

VAST AI releases Triplane Meets Gaussian Splatting on Hugging Face Fast and Generalizable Single-View 3D Reconstruction with Transformers demo: TGS enables fast reconstruction from single-view image. It builds the 3D representation upon a hybrid Triplane-Gaussian representation by evaluating a transformer-based framework, from which 3D Gaussians would be decoded

VAST AI releases Triplane Meets Gaussian Splatting on Hugging Face Fast and Generalizable Single-View 3D Reconstruction with Transformers demo: TGS enables fast reconstruction from single-view image. It builds the 3D representation upon a hybrid Triplane-Gaussian representation by evaluating a transformer-based framework, from which 3D Gaussians would be decoded

AK

113,226 views • 2 years ago

Self-Supervised Learning of Motion Concepts by Optimizing Counterfactuals

Self-Supervised Learning of Motion Concepts by Optimizing Counterfactuals

AK

28,754 views • 1 year ago

Introducing “FlowMap”, the first self-supervised, differentiable structure-from-motion method that is competitive with conventional SfM like Colmap! IMO this solves a major missing piece for internet-scale training of 3D Deep Learning methods. 1/n

Introducing “FlowMap”, the first self-supervised, differentiable structure-from-motion method that is competitive with conventional SfM like Colmap! IMO this solves a major missing piece for internet-scale training of 3D Deep Learning methods. 1/n

Vincent Sitzmann

128,599 views • 2 years ago

Free Machine Learning with Python Course from IBM Topic covered: - Supervised Learning - Unsupervised Learning - Dimensionality Reduction & Collaborative Filtering 100% FREE Course link 🧵👇

Free Machine Learning with Python Course from IBM Topic covered: - Supervised Learning - Unsupervised Learning - Dimensionality Reduction & Collaborative Filtering 100% FREE Course link 🧵👇

Afiz ⚡️

59,880 views • 3 years ago

DreamPhysics: Learning Physical Properties of Dynamic 3D Gaussians from Video Diffusion Priors Code:

DreamPhysics: Learning Physical Properties of Dynamic 3D Gaussians from Video Diffusion Priors Code:

MrNeRF

12,360 views • 2 years ago

Simulation drives robotics progress, but how do we close the reality gap? Introducing GaussGym: an open-source framework for learning locomotion from pixels with ultra-fast parallelized photorealistic rendering across >4,000 iPhone, GrandTour, ARKit, and Veo scenes! Thread 🧵

Simulation drives robotics progress, but how do we close the reality gap? Introducing GaussGym: an open-source framework for learning locomotion from pixels with ultra-fast parallelized photorealistic rendering across >4,000 iPhone, GrandTour, ARKit, and Veo scenes! Thread 🧵

Alejandro Escontrela

108,296 views • 8 months ago

DL3DV-10K: A Large-Scale Scene Dataset for Deep Learning-based 3D Vision paper page: We have witnessed significant progress in deep learning-based 3D vision, ranging from neural radiance field (NeRF) based 3D representation learning to applications in novel view synthesis (NVS). However, existing scene-level datasets for deep learning-based 3D vision, limited to either synthetic environments or a narrow selection of real-world scenes, are quite insufficient. This insufficiency not only hinders a comprehensive benchmark of existing methods but also caps what could be explored in deep learning-based 3D analysis. To address this critical gap, we present DL3DV-10K, a large-scale scene dataset, featuring 51.2 million frames from 10,510 videos captured from 65 types of point-of-interest (POI) locations, covering both bounded and unbounded scenes, with different levels of reflection, transparency, and lighting. We conducted a comprehensive benchmark of recent NVS methods on DL3DV-10K, which revealed valuable insights for future research in NVS. In addition, we have obtained encouraging results in a pilot study to learn generalizable NeRF from DL3DV-10K, which manifests the necessity of a large-scale scene-level dataset to forge a path toward a foundation model for learning 3D representation.

DL3DV-10K: A Large-Scale Scene Dataset for Deep Learning-based 3D Vision paper page: We have witnessed significant progress in deep learning-based 3D vision, ranging from neural radiance field (NeRF) based 3D representation learning to applications in novel view synthesis (NVS). However, existing scene-level datasets for deep learning-based 3D vision, limited to either synthetic environments or a narrow selection of real-world scenes, are quite insufficient. This insufficiency not only hinders a comprehensive benchmark of existing methods but also caps what could be explored in deep learning-based 3D analysis. To address this critical gap, we present DL3DV-10K, a large-scale scene dataset, featuring 51.2 million frames from 10,510 videos captured from 65 types of point-of-interest (POI) locations, covering both bounded and unbounded scenes, with different levels of reflection, transparency, and lighting. We conducted a comprehensive benchmark of recent NVS methods on DL3DV-10K, which revealed valuable insights for future research in NVS. In addition, we have obtained encouraging results in a pilot study to learn generalizable NeRF from DL3DV-10K, which manifests the necessity of a large-scale scene-level dataset to forge a path toward a foundation model for learning 3D representation.

AK

49,917 views • 2 years ago

A little preview of the 3D hair physics and shiny materials! 🩷✨ #VTuber

A little preview of the 3D hair physics and shiny materials! 🩷✨ #VTuber

VLightning 💖✨3D Model Commissions open

25,672 views • 8 days ago

Want a robot that learns household tasks by watching you? EquiBot is a ✨ generalizable and 🚰 data-efficient method for visuomotor policy learning, robust to changes in object shapes, lighting, and scene makeup, even from just 5 mins of human videos. 🧵↓

Want a robot that learns household tasks by watching you? EquiBot is a ✨ generalizable and 🚰 data-efficient method for visuomotor policy learning, robust to changes in object shapes, lighting, and scene makeup, even from just 5 mins of human videos. 🧵↓

Jingyun Yang

88,352 views • 2 years ago

Meet LA-Pose. Our latest model taking Wayve another step towards generalization at scale. LA-Pose employs large-scale self-supervised learning, building strong motion representations for 3D perception from 10.2 million unlabeled driving video snippets, unlike today's strongest approaches that often depend on expensive, carefully curated 3D supervision. With only a lightweight pose head and limited labelled data, LA-Pose achieves: 📷 State-of-the-art camera pose estimation 🌎 Strong zero-shot generalization across diverse driving scenarios 🏷️ Orders of magnitude less labelled data than fully supervised 3D approaches Our full blog post: Explore the full paper here:

Meet LA-Pose. Our latest model taking Wayve another step towards generalization at scale. LA-Pose employs large-scale self-supervised learning, building strong motion representations for 3D perception from 10.2 million unlabeled driving video snippets, unlike today's strongest approaches that often depend on expensive, carefully curated 3D supervision. With only a lightweight pose head and limited labelled data, LA-Pose achieves: 📷 State-of-the-art camera pose estimation 🌎 Strong zero-shot generalization across diverse driving scenarios 🏷️ Orders of magnitude less labelled data than fully supervised 3D approaches Our full blog post: Explore the full paper here:

Wayve

36,410 views • 2 months ago

Over the last few months, we’ve been thinking about how to learn from “off-domain” data - data from non-robot sources like video or simulation. These data sources are not quite good enough to learn policies (even monolithic VLA models) directly, but they still contain lots of information that can be useful for generalizable robot control. How can we develop robot learning models that are able to make use of this type of data for generalizable control? In new work, that we call HAMSTER, we show that VLMs can be useful for enabling robotic learning from off-domain data, but specifically when used through hierarchical VLA architectures. We show that this class of models can learn generalizable robot policies for the real world from large-scale, off-domain data. A 🧵 (1/10)

Over the last few months, we’ve been thinking about how to learn from “off-domain” data - data from non-robot sources like video or simulation. These data sources are not quite good enough to learn policies (even monolithic VLA models) directly, but they still contain lots of information that can be useful for generalizable robot control. How can we develop robot learning models that are able to make use of this type of data for generalizable control? In new work, that we call HAMSTER, we show that VLMs can be useful for enabling robotic learning from off-domain data, but specifically when used through hierarchical VLA architectures. We show that this class of models can learn generalizable robot policies for the real world from large-scale, off-domain data. A 🧵 (1/10)

Abhishek Gupta

11,994 views • 1 year ago

Four-star General Cavoli says Ukraine mastered Patriots fast—and the U.S. is now learning from them.

Four-star General Cavoli says Ukraine mastered Patriots fast—and the U.S. is now learning from them.

UNITED24 Media

108,998 views • 1 year ago

Φ-SO : Physical Symbolic Optimization - Learning Physics from Data 🧠 The Physical Symbolic Optimization package uses deep reinforcement learning to discover physical laws from data. Here is Φ-SO discovering the analytical expression of a damped harmonic oscillator.

Φ-SO : Physical Symbolic Optimization - Learning Physics from Data 🧠 The Physical Symbolic Optimization package uses deep reinforcement learning to discover physical laws from data. Here is Φ-SO discovering the analytical expression of a damped harmonic oscillator.

Jousef Murad

433,149 views • 2 years ago

🚦 Excited introducing Urban-Sim — our new simulator presented at #CVPR2025 as a highlight paper! ⚡️ Fast training with IsaacSim backend 🏙️ Diverse 3D assets for rich urban scenes 🤖 Towards generalizable robots in dynamic urban environments. Webpage:

🚦 Excited introducing Urban-Sim — our new simulator presented at #CVPR2025 as a highlight paper! ⚡️ Fast training with IsaacSim backend 🏙️ Diverse 3D assets for rich urban scenes 🤖 Towards generalizable robots in dynamic urban environments. Webpage:

Bolei Zhou

18,211 views • 1 year ago

For a good evening and night - pixels, pixels, lovely pixels 🥰 And sound of course 🔊 🕹️ Warcraft: Orcs and Humans (1994), PC

For a good evening and night - pixels, pixels, lovely pixels 🥰 And sound of course 🔊 🕹️ Warcraft: Orcs and Humans (1994), PC

PeteRetroZach

14,018 views • 6 months ago

This is one of my favorite videos of Bellsack (283) the game (not the similarly named coin). This is actual gameplay with 3d raytracing and 3d physics. opensource/Apache2.

This is one of my favorite videos of Bellsack (283) the game (not the similarly named coin). This is actual gameplay with 3d raytracing and 3d physics. opensource/Apache2.

Lambda Rick 🏴‍☠️/acc

15,519 views • 5 months ago