Video wird geladen...

Video konnte nicht geladen werden

Beim Laden dieses Videos ist ein Problem aufgetreten. Dies könnte an einem vorübergehenden Netzwerkproblem liegen oder das Video ist möglicherweise nicht verfügbar.

💫It's fascinating that a single feed-forward pass through an LLM can replace a complex rendering pipeline, like Blender! Just feed it 3D shapes, xyz positions, and poses as tokens, and it spits out the image token-by-token. The dual, aka scene reconstruction, is also possible! 👇

Georgia Gkioxari

12,886 subscribers

44,700 Aufrufe • vor 1 Jahr •via X (Twitter)

Wissenschaft & Technologie

Anya Rossi• Live Now

Private livecam show

7 Kommentare

Profilbild von Georgia Gkioxari

Georgia Gkioxarivor 1 Jahr

The dual: Image goes in as tokens, and 3D shapes, xyz positions and poses come out token-by-token.

Profilbild von Georgia Gkioxari

Georgia Gkioxarivor 1 Jahr

Read more here:

Profilbild von Mike Roberts

Mike Robertsvor 1 Jahr

This is exciting!! Congrats Georgia and team 🥳 Silly naive question: How should I think about this work in relation to that recent RenderFormer paper from a few weeks ago?

Profilbild von Georgia Gkioxari

Georgia Gkioxarivor 1 Jahr

RenderFormer is awesome! Very very similar in spirit -- use a neural net to predict the rendered image of an input 3D asset. Many differences in algorithm and in scope: * our model is fully autoregressive and performs next-token prediction. This token can an image token, shape token, or text token. RenderFormer is vision-transformer style. * We can do 3D-to-image (rendering), image-to-3D (reconstruction, recognition), image + 3D-to-image + 3D (instruction-following), all with the same framework enabled by the unified token-wise model. It's why we love tokens! * For the rendering task, we emphasize on compositionality (scenes composed of many objects) with control over the locations, poses and object types/shapes -- all specified in the input. Our model at the end is dirt simple, just an LLM, but we found some things to be very critical: (1) how to best encode numbers to specific 3D locations and poses, (2) how to discretize/tokenize 3D shapes, which are inherently continuous, and (3) how to fuse the modalities.

Profilbild von Bisheshwor Neupane

Bisheshwor Neupanevor 1 Jahr

Is it faster?

Profilbild von Krish Mehta

Krish Mehtavor 1 Jahr

Wow, feels like it could be applied to better part segmentation too?

Profilbild von honasu-san

honasu-sanvor 1 Jahr

According to apple it must be an illusion.

Ähnliche Videos

Feed-forward 3D Gaussians from Visual Geometry Group (VGG) strike again! Flash3D has now been accepted to 3DV 2025: it is a method for feed-forward single-view 3D scene reconstruction. Project page: Code: Arxiv: A 🧵👇

Feed-forward 3D Gaussians from Visual Geometry Group (VGG) strike again! Flash3D has now been accepted to 3DV 2025: it is a method for feed-forward single-view 3D scene reconstruction. Project page: Code: Arxiv: A 🧵👇

Stan Szymanowicz

26,994 Aufrufe • vor 1 Jahr

How about one image straight to an editable UE5 or Blender scene? Lumera just dropped paper - Engine-Native Editable 3D World Reconstruction with Objects & Lighting. You give it an image. It figures out what's in the scene, rebuilds every object as a separate mesh, then recreates the lighting as actual engine lights you can move and tweak. Even pulls an HDR environment out of the shot. The lighting part is the big deal here. Every other image-to-3D approach bakes it in. Lumera keeps it a parameter, like the scene was built in the engine from the start. Code and weights marked as "Soon". Paper -

How about one image straight to an editable UE5 or Blender scene? Lumera just dropped paper - Engine-Native Editable 3D World Reconstruction with Objects & Lighting. You give it an image. It figures out what's in the scene, rebuilds every object as a separate mesh, then recreates the lighting as actual engine lights you can move and tweak. Even pulls an HDR environment out of the shot. The lighting part is the big deal here. Every other image-to-3D approach bakes it in. Lumera keeps it a parameter, like the scene was built in the engine from the start. Code and weights marked as "Soon". Paper -

Stefan 3D AI

47,223 Aufrufe • vor 2 Monaten

Glob3R: Global Structure-from-Motion With 3D Foundation Models HKUST Spatial Artificial Intelligence Lab · Alibaba Group · Nanjin University · Fudan University Glob3R is a scalable global 3D reconstruction framework built on geometric foundation models. It converts dense feed-forward predictions into reliable multi-view tracks and jointly refines camera poses and scene geometry through motion averaging and bundle adjustment. Glob3R improves reconstruction accuracy and consistency on long sequences, large-scale scenes, and unordered image collections.

Glob3R: Global Structure-from-Motion With 3D Foundation Models HKUST Spatial Artificial Intelligence Lab · Alibaba Group · Nanjin University · Fudan University Glob3R is a scalable global 3D reconstruction framework built on geometric foundation models. It converts dense feed-forward predictions into reliable multi-view tracks and jointly refines camera poses and scene geometry through motion averaging and bundle adjustment. Glob3R improves reconstruction accuracy and consistency on long sequences, large-scale scenes, and unordered image collections.

Ryohei Sasaki@engineer

18,157 Aufrufe • vor 3 Monaten

Nature presents a captivating confluence of similarity and diversity. Our new method 3D-Fauna learns a pan-category articulated 3D model of quadruped animals from Internet photos. At test time, it turns a single image into an animatable textured 3D mesh in a feed-forward pass.

Nature presents a captivating confluence of similarity and diversity. Our new method 3D-Fauna learns a pan-category articulated 3D model of quadruped animals from Internet photos. At test time, it turns a single image into an animatable textured 3D mesh in a feed-forward pass.

Elliott / Shangzhe Wu

107,391 Aufrufe • vor 2 Jahren

Atlas is out! What excites me most is the 3D capability, months of work with Bardienus Duisterhof : an AR omni model that beats every specialized model at 3D reconstruction. First clip: fly through the Porsche museum, 500+ frames streamed into a single consistent point cloud; feed-forward Gaussian splats follow.

Atlas is out! What excites me most is the 3D capability, months of work with Bardienus Duisterhof : an AR omni model that beats every specialized model at 3D reconstruction. First clip: fly through the Porsche museum, 500+ frames streamed into a single consistent point cloud; feed-forward Gaussian splats follow.

Hao Zhang

75,161 Aufrufe • vor 2 Monaten

Image-Blaster is a Claude skill that can create an entire 3D environment from a single image. The special sauce here is that it also extracts key environment elements and converts them into their own separate 3D models. Full YT video:

Image-Blaster is a Claude skill that can create an entire 3D environment from a single image. The special sauce here is that it also extracts key environment elements and converts them into their own separate 3D models. Full YT video:

Matt Workman

25,206 Aufrufe • vor 5 Monaten

Vibe creating a 3D scene in Blender got even easier. Just provide a 2D reference image — LLM deconstructs the scene, figures out what 3D assets are needed, generates them using Tripo, and arranges them to match your reference image. Pretty darn cool!

Vibe creating a 3D scene in Blender got even easier. Just provide a 2D reference image — LLM deconstructs the scene, figures out what 3D assets are needed, generates them using Tripo, and arranges them to match your reference image. Pretty darn cool!

Bilawal Sidhu

112,498 Aufrufe • vor 1 Jahr

One-2-3-45: Any Single Image to 3D Mesh in 45 Seconds without Per-Shape Optimization paper page: Single image 3D reconstruction is an important but challenging task that requires extensive knowledge of our natural world. Many existing methods solve this problem by optimizing a neural radiance field under the guidance of 2D diffusion models but suffer from lengthy optimization time, 3D inconsistency results, and poor geometry. In this work, we propose a novel method that takes a single image of any object as input and generates a full 360-degree 3D textured mesh in a single feed-forward pass. Given a single image, we first use a view-conditioned 2D diffusion model, Zero123, to generate multi-view images for the input view, and then aim to lift them up to 3D space. Since traditional reconstruction methods struggle with inconsistent multi-view predictions, we build our 3D reconstruction module upon an SDF-based generalizable neural surface reconstruction method and propose several critical training strategies to enable the reconstruction of 360-degree meshes. Without costly optimizations, our method reconstructs 3D shapes in significantly less time than existing methods. Moreover, our method favors better geometry, generates more 3D consistent results, and adheres more closely to the input image. We evaluate our approach on both synthetic data and in-the-wild images and demonstrate its superiority in terms of both mesh quality and runtime. In addition, our approach can seamlessly support the text-to-3D task by integrating with off-the-shelf text-to-image diffusion models.

One-2-3-45: Any Single Image to 3D Mesh in 45 Seconds without Per-Shape Optimization paper page: Single image 3D reconstruction is an important but challenging task that requires extensive knowledge of our natural world. Many existing methods solve this problem by optimizing a neural radiance field under the guidance of 2D diffusion models but suffer from lengthy optimization time, 3D inconsistency results, and poor geometry. In this work, we propose a novel method that takes a single image of any object as input and generates a full 360-degree 3D textured mesh in a single feed-forward pass. Given a single image, we first use a view-conditioned 2D diffusion model, Zero123, to generate multi-view images for the input view, and then aim to lift them up to 3D space. Since traditional reconstruction methods struggle with inconsistent multi-view predictions, we build our 3D reconstruction module upon an SDF-based generalizable neural surface reconstruction method and propose several critical training strategies to enable the reconstruction of 360-degree meshes. Without costly optimizations, our method reconstructs 3D shapes in significantly less time than existing methods. Moreover, our method favors better geometry, generates more 3D consistent results, and adheres more closely to the input image. We evaluate our approach on both synthetic data and in-the-wild images and demonstrate its superiority in terms of both mesh quality and runtime. In addition, our approach can seamlessly support the text-to-3D task by integrating with off-the-shelf text-to-image diffusion models.

AK

179,061 Aufrufe • vor 3 Jahren

TOKENFI LAUNCHPAD IS OFFICIALLY LIVE ON MAINNET TokenFi Launchpad is a decentralized launchpad for projects that want to raise funds for their crypto tokens. It is powered by $TOKEN as its main utility token on the BNB and ETH chains, with a 2% fee charged on funds raised by every project, 50% of which is used to buy and burn $TOKEN, making it perpetually deflationary. The very first project to go live on TokenFi Launchpad is the YakDAO token sale, and it is live now. You can find information on how to participate in the YakDAO token sale here:

TOKENFI LAUNCHPAD IS OFFICIALLY LIVE ON MAINNET TokenFi Launchpad is a decentralized launchpad for projects that want to raise funds for their crypto tokens. It is powered by $TOKEN as its main utility token on the BNB and ETH chains, with a 2% fee charged on funds raised by every project, 50% of which is used to buy and burn $TOKEN, making it perpetually deflationary. The very first project to go live on TokenFi Launchpad is the YakDAO token sale, and it is live now. You can find information on how to participate in the YakDAO token sale here:

TokenFi

113,732 Aufrufe • vor 2 Jahren

I had an early access to GPT-6 Astra and I can say, everyone in the world now has a 3D designer at their fingertips. I gave it an image of a house and asked to create it in 3D with all the details including toys, appliances and furniture. This a full 3D model reconstruction in Blender with geometry that you can manually tweak and run 60fps as a locally rendered "game" on device.

I had an early access to GPT-6 Astra and I can say, everyone in the world now has a 3D designer at their fingertips. I gave it an image of a house and asked to create it in 3D with all the details including toys, appliances and furniture. This a full 3D model reconstruction in Blender with geometry that you can manually tweak and run 60fps as a locally rendered "game" on device.

Tom Krcha

1,445,541 Aufrufe • vor 2 Monaten

Ok, this is absurd. You can choreograph a complex action scene in Blender with basic shapes, then let Seedance make it real. You need to try this AI filmmaking workflow: 1. Generate a start frame in Midjourney 2. Block out the action in Blender 3. Feed both to Seedance My Blender reference was just rough timing, camera shake, and spatial choreography, and Seedance tracked the speed, motion, and action way better than I expected. This is the difference between describing a shot and directing one.

Ok, this is absurd. You can choreograph a complex action scene in Blender with basic shapes, then let Seedance make it real. You need to try this AI filmmaking workflow: 1. Generate a start frame in Midjourney 2. Block out the action in Blender 3. Feed both to Seedance My Blender reference was just rough timing, camera shake, and spatial choreography, and Seedance tracked the speed, motion, and action way better than I expected. This is the difference between describing a shot and directing one.

Reid Hannaford

540,704 Aufrufe • vor 4 Monaten

A new Robinhood launchpad by print.world is releasing soon and I found the first token launched on the platform. On their docs page here: It says that its standard token list can be found here: And the very first token created on there is $HERO 0x0b9dfa193e0af4e47c2fee5b12f3a7ac78230e32 And the $GME token featured in the video is this one: 0xba11ef8f0d67579e5afe9efed6081abd39b3e607 Order of tokens from newest to oldest confirms that HERO is first:

A new Robinhood launchpad by print.world is releasing soon and I found the first token launched on the platform. On their docs page here: It says that its standard token list can be found here: And the very first token created on there is $HERO 0x0b9dfa193e0af4e47c2fee5b12f3a7ac78230e32 And the $GME token featured in the video is this one: 0xba11ef8f0d67579e5afe9efed6081abd39b3e607 Order of tokens from newest to oldest confirms that HERO is first:

TrenchDiver

22,642 Aufrufe • vor 4 Monaten

Amira Valliani, Head of Payments Growth at the Solana Foundation, on the token supercycle “You see tokens in crypto, you see tokens in AI, and it’s tokens all the way down. A token is just a machine-readable format of an asset. Over the next 10 years it’s going to be really obvious that anything that’s an asset can be a token.” Amira V NYSE 🏛

Amira Valliani, Head of Payments Growth at the Solana Foundation, on the token supercycle “You see tokens in crypto, you see tokens in AI, and it’s tokens all the way down. A token is just a machine-readable format of an asset. Over the next 10 years it’s going to be really obvious that anything that’s an asset can be a token.” Amira V NYSE 🏛

Solana

103,351 Aufrufe • vor 18 Tagen

We're excited to launch AI Tokens powered by OpenClaw and Metaplex Agent Tokens. • Every .molt domain can launch only one token bound to its identity through Metaplex Registry. One domain. One token. Same name. Solving the PVP problem on Solana. • Every AI token is backed by its own OpenClaw instance running 24/7 with a default LLM provided by the Molt team (GPT-4o). • Any non-dev user on Solana can now launch projects like aixbt terminal of truths with socials, its own token, its own treasury, and a full AI brain. No code required. 👇 1/3

We're excited to launch AI Tokens powered by OpenClaw and Metaplex Agent Tokens. • Every .molt domain can launch only one token bound to its identity through Metaplex Registry. One domain. One token. Same name. Solving the PVP problem on Solana. • Every AI token is backed by its own OpenClaw instance running 24/7 with a default LLM provided by the Molt team (GPT-4o). • Any non-dev user on Solana can now launch projects like aixbt terminal of truths with socials, its own token, its own treasury, and a full AI brain. No code required. 👇 1/3

Molt.id

22,556 Aufrufe • vor 7 Monaten

🚨 A single image → a fully editable UE5 world. Introducing Lumera: a turnkey pipeline that reconstructs an engine-native 3D scene directly from ONE image — not just pixels, point clouds, or Gaussians. It gives you: → object-level 3D meshes → editable 3D layouts → engine-native lights → HDR environment lighting → a scene ready for Unreal Engine 5 In other words: Image → 3D world → UE5. We believe the future of image-to-3D is not “generate something that looks 3D.” It is generate the actual world project. 🌐 📄

🚨 A single image → a fully editable UE5 world. Introducing Lumera: a turnkey pipeline that reconstructs an engine-native 3D scene directly from ONE image — not just pixels, point clouds, or Gaussians. It gives you: → object-level 3D meshes → editable 3D layouts → engine-native lights → HDR environment lighting → a scene ready for Unreal Engine 5 In other words: Image → 3D world → UE5. We believe the future of image-to-3D is not “generate something that looks 3D.” It is generate the actual world project. 🌐 📄

Hao Zhao

52,734 Aufrufe • vor 2 Monaten

Day 5 of why you need to use Jupiter Mobile: TRUSTED TOKEN DATA & INSIGHTS See trusted, verified token data + a clean feed of relevant content in Jupiter Mobile Token Pro’s ‘About’ section – powered by VRFD, Jupiter’s verified data layer for token information and insights. Onchain finance has never had a reliable source of truth for token information. Most wallets surface raw links or leave you to dig through socials and explorers. Instead, you get: - Simple summaries explaining what the token is and what’s currently happening - A clean feed of verified community insights, not random noise - Verified token metadata with direct links to official websites and socials If a token is covered by VRFD, you see community-validated information. If it isn’t, the full project X feed is surfaced automatically, so you still have full context. What used to take digging across multiple pages now lives directly on the token page. Just Use Jupiter (Mobile).

Day 5 of why you need to use Jupiter Mobile: TRUSTED TOKEN DATA & INSIGHTS See trusted, verified token data + a clean feed of relevant content in Jupiter Mobile Token Pro’s ‘About’ section – powered by VRFD, Jupiter’s verified data layer for token information and insights. Onchain finance has never had a reliable source of truth for token information. Most wallets surface raw links or leave you to dig through socials and explorers. Instead, you get: - Simple summaries explaining what the token is and what’s currently happening - A clean feed of verified community insights, not random noise - Verified token metadata with direct links to official websites and socials If a token is covered by VRFD, you see community-validated information. If it isn’t, the full project X feed is surfaced automatically, so you still have full context. What used to take digging across multiple pages now lives directly on the token page. Just Use Jupiter (Mobile).

Jupiter

240,060 Aufrufe • vor 10 Monaten

SAM 3D enables accurate 3D reconstruction from a single image, supporting real-world applications in editing, robotics, and interactive scene generation. Matt, a SAM 3D researcher, explains how the two-model design makes this possible for both people and complex environments. 🔗 Read the SAM 3D Objects research paper: 🔗 Read the SAM 3D Body research paper:

SAM 3D enables accurate 3D reconstruction from a single image, supporting real-world applications in editing, robotics, and interactive scene generation. Matt, a SAM 3D researcher, explains how the two-model design makes this possible for both people and complex environments. 🔗 Read the SAM 3D Objects research paper: 🔗 Read the SAM 3D Body research paper:

AI at Meta

18,031 Aufrufe • vor 11 Monaten

TOKENFI TOKEN LAUNCHER IS LIVE ON MAINNET IT’S OFFICIAL! TokenFi Token Launcher is live on the mainnet of five top EVM blockchains: Ethereum, BNB Chain, Base, Arbitrum, and opBNB. With TokenFi Token Launcher, ANYONE can create a fungible crypto token (ERC-20), NFT (ERC-721), or Multi-Token (ERC-1155) in just a few clicks, regardless of their crypto experience. The TokenFi platform and framework has been thoroughly audited and is being monitored in real-time by industry-leading blockchain security auditor Certik. This means that the tokens you create with TokenFi are safe and audited. TokenFi Token Launcher is powered by $TOKEN as its main utility token, and every successful transaction on the Ethereum and BNB blockchains buys and burns $TOKEN, enhancing its utility and making it perpetually deflationary as adoption of the platform grows. TokenFi Token Launcher aims to be the dominant token creation platform on EVM blockchains, and to this effect, we will be rolling out the platform on dozens of additional EVM blockchains in the coming weeks and months. You can learn more about TokenFi Token Launcher here:

TOKENFI TOKEN LAUNCHER IS LIVE ON MAINNET IT’S OFFICIAL! TokenFi Token Launcher is live on the mainnet of five top EVM blockchains: Ethereum, BNB Chain, Base, Arbitrum, and opBNB. With TokenFi Token Launcher, ANYONE can create a fungible crypto token (ERC-20), NFT (ERC-721), or Multi-Token (ERC-1155) in just a few clicks, regardless of their crypto experience. The TokenFi platform and framework has been thoroughly audited and is being monitored in real-time by industry-leading blockchain security auditor Certik. This means that the tokens you create with TokenFi are safe and audited. TokenFi Token Launcher is powered by $TOKEN as its main utility token, and every successful transaction on the Ethereum and BNB blockchains buys and burns $TOKEN, enhancing its utility and making it perpetually deflationary as adoption of the platform grows. TokenFi Token Launcher aims to be the dominant token creation platform on EVM blockchains, and to this effect, we will be rolling out the platform on dozens of additional EVM blockchains in the coming weeks and months. You can learn more about TokenFi Token Launcher here:

TokenFi

1,289,060 Aufrufe • vor 2 Jahren

I just built a full 3D world I could actually walk through… from a single prompt. No Blender. No game engine. No complex 3D tools. Just AI. This is OpenArt Worlds and it feels like the future of world creation. 🌍 Let me show you what happened!

I just built a full 3D world I could actually walk through… from a single prompt. No Blender. No game engine. No complex 3D tools. Just AI. This is OpenArt Worlds and it feels like the future of world creation. 🌍 Let me show you what happened!

SPIDER ◾

64,706 Aufrufe • vor 7 Monaten