Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

📢GaussianGPT (ECCV'26) Code Release📢 What if 3D scenes worked like language? Generate full 3D Gaussian scenes - from scratch or from partial - token by token! 🔗 🌐 Great work by Nicolas von Lützow, Barbara Roessle, Katharina Schmid

MattNiessner's profile picture

Matthias Niessner

50,506 subscribers

58,483 Aufrufe • vor 3 Monaten •via X (Twitter)

Wissenschaft & TechnologieBildung
LIVE

Anya Rossi• Live Now

Private livecam show

12 Kommentare

Profilbild von 科学怪人HC
科学怪人HCvor 3 Monaten

@nicolasvluetzow @barbara_roessle @katha_schmid 有点像3d打印高斯一样

Profilbild von Chukwudalu Dumebi-Kachikwu
Chukwudalu Dumebi-Kachikwuvor 3 Monaten

@nicolasvluetzow @barbara_roessle @katha_schmid This is amazing

Profilbild von whatsupfranks
whatsupfranksvor 3 Monaten

@RadianceFields @nicolasvluetzow @barbara_roessle @katha_schmid Are the weights released?

Profilbild von Kristian Calloway
Kristian Callowayvor 2 Monaten

Hello Matthias, I'd love to work with you on a piece but I can't send you a dm. Please send me one whenever you are free

Profilbild von Matthias Niessner
Matthias Niessnervor 2 Monaten

Just send me an email?

Profilbild von Sai Kiran Dev
Sai Kiran Devvor 3 Monaten

@nicolasvluetzow @barbara_roessle @katha_schmid Cool

Profilbild von ζ Pedram ζ
ζ Pedram ζvor 3 Monaten

@nicolasvluetzow @barbara_roessle @katha_schmid Nice

Profilbild von Nick Cassab
Nick Cassabvor 3 Monaten

@nicolasvluetzow @barbara_roessle @katha_schmid Very cool

Profilbild von AI Mastery Guide
AI Mastery Guidevor 3 Monaten

@nicolasvluetzow @barbara_roessle @katha_schmid Treating 3D scenes like a language and generating them token by token is such a clean way to think about the problem.

Profilbild von imaginary
imaginaryvor 3 Monaten

designed a camera that could capture 3d scenes rather than 2d snapshots of them. all you have to do is measure every photon's angle of incidence and frequency that the camera captures. You forgo the lens, too, and with some algorithms, have the camera build the scene in one shot.

Profilbild von goodtothinkwith
goodtothinkwithvor 3 Monaten

@nicolasvluetzow @barbara_roessle @katha_schmid That is really cool

Profilbild von Geospatial FM
Geospatial FMvor 3 Monaten

@nicolasvluetzow @barbara_roessle @katha_schmid Mind blown and I don’t even know what this means

Ähnliche Videos

📢GaussianGPT: autoregressive 3D Gaussian scene generation. We introduce a GPT-style model that directly generates 3D Gaussian scenes, token by token, in a series of small, discrete decision steps. Generation, completion, and large-scale outpainting in a single pipeline. Unlike diffusion-based approaches, GaussianGPT explicitly models the scene distribution at every step, allowing for quite flexible scene synthesis. 🌐 ▶️ Great work by Nicolas von Lützow, Barbara Roessle, Katharina Schmid
0:30

📢GaussianGPT: autoregressive 3D Gaussian scene generation. We introduce a GPT-style model that directly generates 3D Gaussian scenes, token by token, in a series of small, discrete decision steps. Generation, completion, and large-scale outpainting in a single pipeline. Unlike diffusion-based approaches, GaussianGPT explicitly models the scene distribution at every step, allowing for quite flexible scene synthesis. 🌐 ▶️ Great work by Nicolas von Lützow, Barbara Roessle, Katharina Schmid

Matthias Niessner

152,704 Aufrufe • vor 7 Monaten

📢 GenRecon Code Release 📢 Few images in → complete, high-fidelity 3D scene out! GenRecon builds a generative prior on full scenes, resulting in unprecedented 3D reconstruction quality. 🔗 🌐 📄
0:20

📢 GenRecon Code Release 📢 Few images in → complete, high-fidelity 3D scene out! GenRecon builds a generative prior on full scenes, resulting in unprecedented 3D reconstruction quality. 🔗 🌐 📄

Matthias Niessner

40,528 Aufrufe • vor 3 Monaten

📢📢GenRecon: Bridging Generative Priors for Multi-View 3D Scene Reconstruction📢📢 Reconstructing high-fidelity 3D scenes from sparse RGB input is hard. It needs a strong 3D prior! We reformulate multi-view scene reconstruction as conditional 3D generation over overlapping spatial chunks, lifting posed image features into a generative shape prior via 3D conditioning. As an example prior, we build on Trellis2, and train it such that its reconstruction is pixel aligned and matches from all views. GenRecon achieves unprecedented reconstruction quality from any sparse RGB input sequence, even from a phone capture. The reconstruction also includes PBR materials which facilitates relighting and virtual object insertion. Amazing work by Katharina Schmid, Nicolas von Lützow, Jozef, Angela Dai
0:26

📢📢GenRecon: Bridging Generative Priors for Multi-View 3D Scene Reconstruction📢📢 Reconstructing high-fidelity 3D scenes from sparse RGB input is hard. It needs a strong 3D prior! We reformulate multi-view scene reconstruction as conditional 3D generation over overlapping spatial chunks, lifting posed image features into a generative shape prior via 3D conditioning. As an example prior, we build on Trellis2, and train it such that its reconstruction is pixel aligned and matches from all views. GenRecon achieves unprecedented reconstruction quality from any sparse RGB input sequence, even from a phone capture. The reconstruction also includes PBR materials which facilitates relighting and virtual object insertion. Amazing work by Katharina Schmid, Nicolas von Lützow, Jozef, Angela Dai

Matthias Niessner

18,447 Aufrufe • vor 5 Monaten

HoloDreamer can generate enclosed 3D scenes from text descriptions! It does so by first creating a high-quality equirectangular panorama and then rapidly reconstructing the 3D scene using 3D Gaussian Splatting. Links ⬇️
0:36

HoloDreamer can generate enclosed 3D scenes from text descriptions! It does so by first creating a high-quality equirectangular panorama and then rapidly reconstructing the 3D scene using 3D Gaussian Splatting. Links ⬇️

Dreaming Tulpa 🥓👑

59,422 Aufrufe • vor 2 Jahren

Super excited for #ECCV'26 in Malmö! Our group will present a series of cutting-edge works, including two orals and a spotlight, around generative AI that cover 3D scene generation, photo-realistic avatars, agentic modeling, and much more! I'll also give several workshop talks about our recent research, including a few exciting updates what we're cooking at SpAItial AI :) 1. GaussianGPT: Towards Autoregressive 3D Gaussian Scene Generation *(oral)* 2. TriFlow: Generating Artist-Like 3D Mesh Topology via Nearest-Vertex Vector Fields *(oral)* 3. Face Anything: 4D Face Reconstruction from Any Image Sequence *(spotlight)* 4. Pix2NPHM: Learning to Regress NPHM Reconstructions From a Single Image 5. Seen2Scene: Completing Realistic 3D Scenes with Visibility-Guided Flow 6. DreamEdit3D: Personalization of Multi-View Diffusion Models for 3D Editing 7. WorldAgents: Can Foundation Image Models be Agents for 3D World Models? 8. World Reconstruction From Inconsistent Views 9. Head Avatars with Dynamic Explicit Hair Great work by Nicolas von Lützow Haoxuan Li Ziya Erkoç Umut Kocasarı Vanessa Sklyarova Lukas Höllein Quan Meng Jinxin Ai Simon Giebenhain and all amazing collaborators!
0:27

Super excited for #ECCV'26 in Malmö! Our group will present a series of cutting-edge works, including two orals and a spotlight, around generative AI that cover 3D scene generation, photo-realistic avatars, agentic modeling, and much more! I'll also give several workshop talks about our recent research, including a few exciting updates what we're cooking at SpAItial AI :) 1. GaussianGPT: Towards Autoregressive 3D Gaussian Scene Generation *(oral)* 2. TriFlow: Generating Artist-Like 3D Mesh Topology via Nearest-Vertex Vector Fields *(oral)* 3. Face Anything: 4D Face Reconstruction from Any Image Sequence *(spotlight)* 4. Pix2NPHM: Learning to Regress NPHM Reconstructions From a Single Image 5. Seen2Scene: Completing Realistic 3D Scenes with Visibility-Guided Flow 6. DreamEdit3D: Personalization of Multi-View Diffusion Models for 3D Editing 7. WorldAgents: Can Foundation Image Models be Agents for 3D World Models? 8. World Reconstruction From Inconsistent Views 9. Head Avatars with Dynamic Explicit Hair Great work by Nicolas von Lützow Haoxuan Li Ziya Erkoç Umut Kocasarı Vanessa Sklyarova Lukas Höllein Quan Meng Jinxin Ai Simon Giebenhain and all amazing collaborators!

Matthias Niessner

15,338 Aufrufe • vor 1 Monat

Liaonomics Explained — How ATOSHI’s token release mechanism works. Team ATOSHI 🌐 Mining Made Simple. Powered By Community. 📢 X:
1:59

Liaonomics Explained — How ATOSHI’s token release mechanism works. Team ATOSHI 🌐 Mining Made Simple. Powered By Community. 📢 X:

ATOSHI

28,766 Aufrufe • vor 20 Tagen

📢 LinPrim: Linear Primitives for Differentiable Volumetric Rendering 📢 We use octahedra or tetrahedra as explicit as volumetric building blocks for gradient-based novel view synthesis - as an alternative to 3D Gaussians with discrete, bounded geometry. We show how it can be used to reconstruct photorealistic scenes, and introduce a corresponding differentiable CUDA rasterizer that enables real-time rendering. On real-world scenes, LinPrim achieves comparable image quality with fewer primitives, adding a practical polyhedral option to the 3D scene representation toolbox and expanding the known design space. 🌍 🎥 Amazing work by Nicolas von Lützow!
0:35

📢 LinPrim: Linear Primitives for Differentiable Volumetric Rendering 📢 We use octahedra or tetrahedra as explicit as volumetric building blocks for gradient-based novel view synthesis - as an alternative to 3D Gaussians with discrete, bounded geometry. We show how it can be used to reconstruct photorealistic scenes, and introduce a corresponding differentiable CUDA rasterizer that enables real-time rendering. On real-world scenes, LinPrim achieves comparable image quality with fewer primitives, adding a practical polyhedral option to the 3D scene representation toolbox and expanding the known design space. 🌍 🎥 Amazing work by Nicolas von Lützow!

Matthias Niessner

11,425 Aufrufe • vor 1 Jahr

📢𝐋𝟑𝐃𝐆: 𝐋𝐚𝐭𝐞𝐧𝐭 𝟑𝐃 𝐆𝐚𝐮𝐬𝐬𝐢𝐚𝐧 𝐃𝐢𝐟𝐟𝐮𝐬𝐢𝐨𝐧📢 #SIGGRAPHAsia We propose a generative diffusion model for 3D Gaussians. Key is a learnt latent space which substantially reduces the complexity of the diffusion process, thus facilitating room-scale scene generation! Great work by Barbara Roessle in with Norman Müller, Angela Dai, Lorenzo Porzi, Samuel Rota Bulò, Peter Kontschieder!
0:20

📢𝐋𝟑𝐃𝐆: 𝐋𝐚𝐭𝐞𝐧𝐭 𝟑𝐃 𝐆𝐚𝐮𝐬𝐬𝐢𝐚𝐧 𝐃𝐢𝐟𝐟𝐮𝐬𝐢𝐨𝐧📢 #SIGGRAPHAsia We propose a generative diffusion model for 3D Gaussians. Key is a learnt latent space which substantially reduces the complexity of the diffusion process, thus facilitating room-scale scene generation! Great work by Barbara Roessle in with Norman Müller, Angela Dai, Lorenzo Porzi, Samuel Rota Bulò, Peter Kontschieder!

Matthias Niessner

39,529 Aufrufe • vor 2 Jahren

Gemini 3.0 Pro is at great 3D design and front-end. It can generate complex 3D scenes and Three.js objects from text prompts. Here's a nice retro-future example from cris.
0:37

Gemini 3.0 Pro is at great 3D design and front-end. It can generate complex 3D scenes and Three.js objects from text prompts. Here's a nice retro-future example from cris.

Addy Osmani

90,189 Aufrufe • vor 10 Monaten

📢WorldMesh is accepted to #ECCV2026, and we're releasing the code today! 🎉 Led by mschneider456: navigable, multi-room 3D scenes from a text prompt, with a mesh scaffold conditioning image diffusion for global consistency + photorealistic detail 👇
0:36

📢WorldMesh is accepted to #ECCV2026, and we're releasing the code today! 🎉 Led by mschneider456: navigable, multi-room 3D scenes from a text prompt, with a mesh scaffold conditioning image diffusion for global consistency + photorealistic detail 👇

Angela Dai

43,076 Aufrufe • vor 3 Monaten

📢 FaceAnything (ECCV 2026) Code Release 📢 Turn any image sequence into high-fidelity 4D face reconstructions, without controlled capture rigs. Try it on Hugging Face & reconstruct your face in 4D! 🔗 🤗 🌐
0:24

📢 FaceAnything (ECCV 2026) Code Release 📢 Turn any image sequence into high-fidelity 4D face reconstructions, without controlled capture rigs. Try it on Hugging Face & reconstruct your face in 4D! 🔗 🤗 🌐

Matthias Niessner

49,030 Aufrufe • vor 3 Monaten

3D scenes, built locally. Describe what you want in plain language. Edge0 can generate a structured 3D scene, then modify and refine it on your phone or PC. No project data leaves the device.
0:27

3D scenes, built locally. Describe what you want in plain language. Edge0 can generate a structured 3D scene, then modify and refine it on your phone or PC. No project data leaves the device.

Samuel Zeng

21,642 Aufrufe • vor 1 Monat

PhysX-Anything: creates simulation-ready, articulated 3D assets from a single image; VLM-based model using a new 3D representation that reduces token count by 193x
1:01

PhysX-Anything: creates simulation-ready, articulated 3D assets from a single image; VLM-based model using a new 3D representation that reduces token count by 193x

Wildminder

49,896 Aufrufe • vor 11 Monaten

📢 A Recipe for Generating 3D Worlds From a Single Image 📢 Our recipe explains how existing generative models can be adapted with minimal training effort to generate 3D worlds from a single input image.
0:28

📢 A Recipe for Generating 3D Worlds From a Single Image 📢 Our recipe explains how existing generative models can be adapted with minimal training effort to generate 3D worlds from a single input image.

Katja Schwarz

14,176 Aufrufe • vor 1 Jahr

📢 Intrinsic Image Fusion for Multi-View 3D Material Reconstruction 📢 We combine generative material priors with inverse path tracing: 1) define a parametric texture space 2) fuse monocular predictions across views into consistent textures 3) optimize low-dimensional parameters for physically-grounded reconstructions. The results are relightable PBR textures for 3D scenes: check out the result on a real-world 3D scan from the ScanNet++ dataset! 🌍 🎥 Great work by Peter Kocsis Lukas Höllein!
0:31

📢 Intrinsic Image Fusion for Multi-View 3D Material Reconstruction 📢 We combine generative material priors with inverse path tracing: 1) define a parametric texture space 2) fuse monocular predictions across views into consistent textures 3) optimize low-dimensional parameters for physically-grounded reconstructions. The results are relightable PBR textures for 3D scenes: check out the result on a real-world 3D scan from the ScanNet++ dataset! 🌍 🎥 Great work by Peter Kocsis Lukas Höllein!

Matthias Niessner

23,285 Aufrufe • vor 10 Monaten

HUGE NEWS for 3D Gaussian Splatting! 📢 The PlayCanvas Engine adopts SOGS for 20x Compression of 3DGS. 🗜️ Load HUGE splat scenes even on mobile! 📱 Read More:
0:32

HUGE NEWS for 3D Gaussian Splatting! 📢 The PlayCanvas Engine adopts SOGS for 20x Compression of 3DGS. 🗜️ Load HUGE splat scenes even on mobile! 📱 Read More:

PlayCanvas

22,664 Aufrufe • vor 1 Jahr

📢Animating the Uncaptured 📢 We animate 3D humanoid meshes using video diffusion priors given a text prompt. 🎥 🌍 Realistic motion generation for 3D characters - without motion capture! 🚀 Great work by Marc Benedí Angela Dai
0:24

📢Animating the Uncaptured 📢 We animate 3D humanoid meshes using video diffusion priors given a text prompt. 🎥 🌍 Realistic motion generation for 3D characters - without motion capture! 🚀 Great work by Marc Benedí Angela Dai

Matthias Niessner

11,716 Aufrufe • vor 1 Jahr

Introducing Higgsfield 3D Jutsu, powered by GPT-6 Astra. Turn a single prompt into a fully editable, interactive 3D world. > Generate complex 3D scenes from text > Control geometry, layout, and details > Refine environment instantly with simple prompts Now live on Higgsfield.
0:59

Introducing Higgsfield 3D Jutsu, powered by GPT-6 Astra. Turn a single prompt into a fully editable, interactive 3D world. > Generate complex 3D scenes from text > Control geometry, layout, and details > Refine environment instantly with simple prompts Now live on Higgsfield.

Higgsfield AI 🧩

99,987 Aufrufe • vor 1 Monat

Robots that navigate grocery stores with semantic 3D maps created by language-augmented gaussian splats
0:26

Robots that navigate grocery stores with semantic 3D maps created by language-augmented gaussian splats

Towaki Takikawa / 瀧川永遠希

48,814 Aufrufe • vor 1 Jahr