Loading video...

Video Failed to Load

Go Home

3D Gaussian is great, but how can you interact with it 🌹👋? Introducing #PhysDreamer: Create your own realistic interactive 3D assets from only static images! Discover how we do this below👇 🧵1/: Website:

tianyuanzhang99's profile picture

Tianyuan Zhang

2,216 subscribers

60,953 views • 2 years ago •via X (Twitter)

#PhysDreamer
LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

3D Gaussian Splatting is great, but can it work without the pre-computed camera poses? Introducing: COLMAP-Free 3D Gaussian Splatting Our recent work shows not only it can, but 3D Gaussians make camera pose estimation easy (compared to NeRF) along with reconstruction. 👇🧵
0:50

3D Gaussian Splatting is great, but can it work without the pre-computed camera poses? Introducing: COLMAP-Free 3D Gaussian Splatting Our recent work shows not only it can, but 3D Gaussians make camera pose estimation easy (compared to NeRF) along with reconstruction. 👇🧵

Xiaolong Wang

76,747 views • 2 years ago

3D Gaussian Splats are cool, but they're static (Part 13). VR-GS makes it possible for users to interact with 3D Gaussian kernels in VR and can generate realistic dynamic responses and illumination in real-time.
0:30

3D Gaussian Splats are cool, but they're static (Part 13). VR-GS makes it possible for users to interact with 3D Gaussian kernels in VR and can generate realistic dynamic responses and illumination in real-time.

Dreaming Tulpa 🥓👑

73,759 views • 2 years ago

Our research introduces a system that enables you to generate 3D environments from text prompts and train embodied AI agents within them! Website: Code: How did we leverage Objaverse assets to create interactive 3D environments? 👇
0:32

Our research introduces a system that enables you to generate 3D environments from text prompts and train embodied AI agents within them! Website: Code: How did we leverage Objaverse assets to create interactive 3D environments? 👇

Fan-Yun Sun

35,981 views • 2 years ago

#ICCV2025 🤩3D world generation is cool, but it is cooler to play with the worlds using 3D actions 👆💨, and see what happens! — Introducing *WonderPlay*: Now you can create dynamic 3D scenes that respond to your 3D actions from a single image! Web: 🧵1/7
0:46

#ICCV2025 🤩3D world generation is cool, but it is cooler to play with the worlds using 3D actions 👆💨, and see what happens! — Introducing *WonderPlay*: Now you can create dynamic 3D scenes that respond to your 3D actions from a single image! Web: 🧵1/7

Hong-Xing (Koven) Yu

57,935 views • 1 year ago

Many works model 3D virtual humans, but how can we create realistic dense crowds? At SIGGRAPH Asia 2024, we will show that solving human-human interactions is key to modeling realistic crowds. project: 🧵1/4
0:38

Many works model 3D virtual humans, but how can we create realistic dense crowds? At SIGGRAPH Asia 2024, we will show that solving human-human interactions is key to modeling realistic crowds. project: 🧵1/4

Dan Casas

22,771 views • 2 years ago

Project Genie lets you create and explore your own infinite, interactive worlds. Here's how it works (1/6) 🧵↓
0:37

Project Genie lets you create and explore your own infinite, interactive worlds. Here's how it works (1/6) 🧵↓

Google

98,814 views • 7 months ago

3D AI is advancing quicker than we ever thought possible. Right now, we can use it to create individual 3D assets, but soon, building entire virtual worlds with just a text prompt could become a reality. This is from Meta 3D AI team.
0:32

3D AI is advancing quicker than we ever thought possible. Right now, we can use it to create individual 3D assets, but soon, building entire virtual worlds with just a text prompt could become a reality. This is from Meta 3D AI team.

el.cine

42,166 views • 1 year ago

Create compositions like a PRO by combining 3D with AI! I'll show how to take full control of your scene and generate images in any style you want. Breaking it all down for you in this thread. 🧵👇
0:21

Create compositions like a PRO by combining 3D with AI! I'll show how to take full control of your scene and generate images in any style you want. Breaking it all down for you in this thread. 🧵👇

TechHalla

158,103 views • 1 year ago

this is the future of education teachers vibe coding interactive apps with custom 3D models instead of boring slides. Make your own assets with Tripo this way 👇
0:29

this is the future of education teachers vibe coding interactive apps with custom 3D models instead of boring slides. Make your own assets with Tripo this way 👇

TechHalla

45,010 views • 3 months ago

🚀 PixVerse just launched Interactive Live Avatars — and it’s insane! Now you can create your own AI avatar and interact with it in real time. Not just a video… a fully live, responsive experience. Here’s how it works 🧵 #PixVerseR1 PixVerse
0:26

🚀 PixVerse just launched Interactive Live Avatars — and it’s insane! Now you can create your own AI avatar and interact with it in real time. Not just a video… a fully live, responsive experience. Here’s how it works 🧵 #PixVerseR1 PixVerse

Riya Ai

30,866 views • 4 months ago

Create your own 3D models with AI including · High-quality textures · Riggin · Animations ready in minutes for your filmmaking or game dev projects. Tripo makes it possible, and I’ll show you how below 👇
0:20

Create your own 3D models with AI including · High-quality textures · Riggin · Animations ready in minutes for your filmmaking or game dev projects. Tripo makes it possible, and I’ll show you how below 👇

TechHalla

453,052 views • 8 months ago

⚡️ Introducing Bolt3D ⚡️ Bolt3D generates interactive 3D scenes in less than 7 seconds on a single GPU from one or more images. It features a latent diffusion model that *directly* generates 3D Gaussians of seen and unseen regions, without any test time optimization. 🧵👇 (1/9)
0:20

⚡️ Introducing Bolt3D ⚡️ Bolt3D generates interactive 3D scenes in less than 7 seconds on a single GPU from one or more images. It features a latent diffusion model that *directly* generates 3D Gaussians of seen and unseen regions, without any test time optimization. 🧵👇 (1/9)

Stan Szymanowicz

126,073 views • 1 year ago

1/🧵Gaming is evolving. The way people will interact with the internet and with eachother is changing. The metaverse 2.0 is coming. As the 3D internet. A place where you meet people and interact. Social and immersive experiences. But will you truly own your place in it? 🎮🌍
4:14

1/🧵Gaming is evolving. The way people will interact with the internet and with eachother is changing. The metaverse 2.0 is coming. As the 3D internet. A place where you meet people and interact. Social and immersive experiences. But will you truly own your place in it? 🎮🌍

DS 🪝🧬🟧🟦🍌🦍🧪

80,923 views • 1 year ago

Have you ever wondered how Dany Bittel makes such insane Gaussian Splat scans? The secret is a technique called Focus Stacking—and every 3D creator should know it. 🧵 👇
0:22

Have you ever wondered how Dany Bittel makes such insane Gaussian Splat scans? The secret is a technique called Focus Stacking—and every 3D creator should know it. 🧵 👇

KIRI Engine - 3D Scanner App

41,553 views • 2 months ago

You can now turn images into explorable 3D worlds. Locally. For free. The method involves piloting a virtual 360 degree drone through your scene to map out your world and generate a synthetic dataset for gaussian splat training. Here is how it works 👇
0:22

You can now turn images into explorable 3D worlds. Locally. For free. The method involves piloting a virtual 360 degree drone through your scene to map out your world and generate a synthetic dataset for gaussian splat training. Here is how it works 👇

Mickmumpitz

53,234 views • 9 days ago

🚨 Introducing 'Dreamia'🌱 Watch the full keynote from Mike OC at NFC Lisbon now to discover how our cutting-edge AI character engine is designed to revolutionise how players interact with NPCs in virtual worlds. What do you think? We'd love to hear your thoughts below👇
9:51

🚨 Introducing 'Dreamia'🌱 Watch the full keynote from Mike OC at NFC Lisbon now to discover how our cutting-edge AI character engine is designed to revolutionise how players interact with NPCs in virtual worlds. What do you think? We'd love to hear your thoughts below👇

Youmio

39,919 views • 2 years ago

This new AI tool is interesting! ReconX can create a 3D scene using just two images from different angles. Imagine if we could train our character with only 2 images instead of 10?
0:22

This new AI tool is interesting! ReconX can create a 3D scene using just two images from different angles. Imagine if we could train our character with only 2 images instead of 10?

el.cine

69,436 views • 1 year ago

“This took less than an hour." Interactive 3D is becoming essential across industries - but for a lot of teams, it’s still out of reach. That’s why we built Unity Studio - an intuitive, web-based, no-code editor that helps teams across industries, from manufacturing to retail, turn existing 3D assets into interactive experiences, straight from the browser. Check out what it looks like to go from a static 3D file to a fully interactive demo in under an hour. 🔗 Try it out yourself with a free 30 day Unity Studio trial:
1:01

“This took less than an hour." Interactive 3D is becoming essential across industries - but for a lot of teams, it’s still out of reach. That’s why we built Unity Studio - an intuitive, web-based, no-code editor that helps teams across industries, from manufacturing to retail, turn existing 3D assets into interactive experiences, straight from the browser. Check out what it looks like to go from a static 3D file to a fully interactive demo in under an hour. 🔗 Try it out yourself with a free 30 day Unity Studio trial:

Unity

10,408 views • 3 months ago

📢 I’m testing ViggleAI new AI tool, PINOC, and it’s seriously impressive. You can create 3D Gaussian splatting models from just one image and animate them with a video! It’s the first AI I’ve tried that can animate Gaussian splatting models. I also talked to someone from Viggle, and they might add the option to import your own Gaussian splatting models and animate them. If that happens, I’ll probably make a video tutorial showing how to boost the detail level of a Gaussian splatting model by 4x to create highly realistic animated characters.
1:06

📢 I’m testing ViggleAI new AI tool, PINOC, and it’s seriously impressive. You can create 3D Gaussian splatting models from just one image and animate them with a video! It’s the first AI I’ve tried that can animate Gaussian splatting models. I also talked to someone from Viggle, and they might add the option to import your own Gaussian splatting models and animate them. If that happens, I’ll probably make a video tutorial showing how to boost the detail level of a Gaussian splatting model by 4x to create highly realistic animated characters.

Alex

29,776 views • 3 months ago