Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

Here’s something you didn’t know LLMs can do – reconstruct articulated objects! Introducing Real2Code – our new real2sim approach that scalably reconstructs complex, multi-part articulated objects.

ZhaoMandi's profile picture

Mandi Zhao

5,016 subscribers

91,951 Aufrufe • vor 2 Jahren •via X (Twitter)

BildungNachrichten & PolitikWissenschaft & Technologie
LIVE

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

Two months ago, at an RSS workshop panel, I said that general real2sim reconstruction is still far from solved, especially for articulated objects, which will be a major bottleneck for robotics. But now that has totally changed with Astra; using several photos as input, we can easily reconstruct vivid articulated scenes. The result is so impressive! Excited to see how it will shift the paradigm of real2sim2real and agentic learning for robotics and humanoids.
0:12

Two months ago, at an RSS workshop panel, I said that general real2sim reconstruction is still far from solved, especially for articulated objects, which will be a major bottleneck for robotics. But now that has totally changed with Astra; using several photos as input, we can easily reconstruct vivid articulated scenes. The result is so impressive! Excited to see how it will shift the paradigm of real2sim2real and agentic learning for robotics and humanoids.

Siyuan Huang

19,361 Aufrufe • vor 1 Monat

Mirror Mirror! simple approach to complex subd cylindrical objects
0:13

Mirror Mirror! simple approach to complex subd cylindrical objects

Pilgrim

52,749 Aufrufe • vor 1 Jahr

Wouldn’t it be nice if ChatGPT could find your missing keys for you? Our latest research from Berkeley AI Research + Google AI suggests that robots can use large language models (LLMs) to find hidden objects faster. 🧵👇
0:15

Wouldn’t it be nice if ChatGPT could find your missing keys for you? Our latest research from Berkeley AI Research + Google AI suggests that robots can use large language models (LLMs) to find hidden objects faster. 🧵👇

Kaushik Shivakumar

58,523 Aufrufe • vor 3 Jahren

Introducing 📦𝗔𝗿𝘁𝗶𝗟𝗮𝘁𝗲𝗻𝘁🔧 (SIGGRAPH Asia 2025) — a high-quality 3D diffusion model that explicitly models object articulation, paving the way for richer, more realistic assets in embodied AI and simulation: – Generates fully articulated 3D objects – Physically plausible joints & motion – High-fidelity 3D Gaussian appearance – Supports generation from a single real image arXiv: Project: Code (coming soon):
0:16

Introducing 📦𝗔𝗿𝘁𝗶𝗟𝗮𝘁𝗲𝗻𝘁🔧 (SIGGRAPH Asia 2025) — a high-quality 3D diffusion model that explicitly models object articulation, paving the way for richer, more realistic assets in embodied AI and simulation: – Generates fully articulated 3D objects – Physically plausible joints & motion – High-fidelity 3D Gaussian appearance – Supports generation from a single real image arXiv: Project: Code (coming soon):

Xingang Pan

11,574 Aufrufe • vor 11 Monaten

Introducing Smart Select. You can now detect and separate props, characters, and objects from your image in just one click.
0:16

Introducing Smart Select. You can now detect and separate props, characters, and objects from your image in just one click.

Morphic

79,239 Aufrufe • vor 1 Jahr

📢 LiteReality: Graphics-Ready 3D Scene Reconstruction from RGB-D Scans🏠✨ -> converts RGB-D scans into compact, realistic, and interactive 3D scenes — featuring high-quality meshes, PBR materials, and articulated objects. 📷 🌍
0:19

📢 LiteReality: Graphics-Ready 3D Scene Reconstruction from RGB-D Scans🏠✨ -> converts RGB-D scans into compact, realistic, and interactive 3D scenes — featuring high-quality meshes, PBR materials, and articulated objects. 📷 🌍

Matthias Niessner

23,912 Aufrufe • vor 1 Jahr

Advanced 3D printer creating multi-colored objects with five extruders
0:16

Advanced 3D printer creating multi-colored objects with five extruders

Massimo

46,906 Aufrufe • vor 1 Jahr

New analysis panel in NimbusImage let's you do flow cytometry-style gating on your objects!
0:14

New analysis panel in NimbusImage let's you do flow cytometry-style gating on your objects!

Arjun Raj

24,889 Aufrufe • vor 1 Monat

Our next guest Will brIng a trunk full of exciting new obJectS to the party! 👀 What do you thinK will be inside? 😉
0:15

Our next guest Will brIng a trunk full of exciting new obJectS to the party! 👀 What do you thinK will be inside? 😉

House Party

10,752 Aufrufe • vor 3 Jahren

Freepik just dropped Objects A total game changer for creatives. You can generate images with exciting items or train your own LoRA. The best part you can mix it with Custom Characters & Styles, colors... Endless possibilities. My Lora + objects + Veo 2
0:14

Freepik just dropped Objects A total game changer for creatives. You can generate images with exciting items or train your own LoRA. The best part you can mix it with Custom Characters & Styles, colors... Endless possibilities. My Lora + objects + Veo 2

Amira Zairi

28,977 Aufrufe • vor 1 Jahr

Prototyping a Multi-Paint script I made that will temporarily join and separate objects using vertex groups!
0:14

Prototyping a Multi-Paint script I made that will temporarily join and separate objects using vertex groups!

Shadsterwolf

24,577 Aufrufe • vor 3 Jahren

You can even reimagine the action in a video you took by asking Gemini Omni. Transform your world instantly - change the environment, add new objects, or create something completely unexpected.
0:05

You can even reimagine the action in a video you took by asking Gemini Omni. Transform your world instantly - change the environment, add new objects, or create something completely unexpected.

Google DeepMind

48,103 Aufrufe • vor 5 Monaten

You can select and edit several objects at the same time.
0:13

You can select and edit several objects at the same time.

Canvas of Kings | Might of Merchants

62,364 Aufrufe • vor 1 Jahr

Golden Rule- If you can avoid driving over objects on the road surface - Do it!! #ArriveAlive #Hijacking #CarJacking #Crime
0:12

Golden Rule- If you can avoid driving over objects on the road surface - Do it!! #ArriveAlive #Hijacking #CarJacking #Crime

Arrive Alive

180,844 Aufrufe • vor 3 Jahren

multi-player, multi-view, llm generated shared 3d objects *this palm tree cost about 1.3 cents using gpt-4o
0:18

multi-player, multi-view, llm generated shared 3d objects *this palm tree cost about 1.3 cents using gpt-4o

Yohei

25,131 Aufrufe • vor 1 Jahr

introducing Video Training, a new level of control for AI video generation. now you can train Wan 2.1 with your own videos and have it learn custom styles, motions, or objects. here's how it works 👇
0:14

introducing Video Training, a new level of control for AI video generation. now you can train Wan 2.1 with your own videos and have it learn custom styles, motions, or objects. here's how it works 👇

Krea

129,115 Aufrufe • vor 1 Jahr

Our new Clutter system is in — effortlessly fill your maps with procedurally placed objects 🤯
0:14

Our new Clutter system is in — effortlessly fill your maps with procedurally placed objects 🤯

s&box

192,547 Aufrufe • vor 8 Monaten