Загрузка видео...

Не удалось загрузить видео

Возникла проблема при загрузке этого видео. Это может быть связано с временными проблемами сети или видео может быть недоступно.

На главную

📢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

Matthias Niessner

50,294 subscribers

58,422 просмотров • 3 месяцев назад •via X (Twitter)

Наука и технологии Образование

Anya Rossi• Live Now

Private livecam show

Комментарии: 12

Фото профиля 科学怪人HC

科学怪人HC3 месяцев назад

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

Фото профиля Chukwudalu Dumebi-Kachikwu

Chukwudalu Dumebi-Kachikwu3 месяцев назад

@nicolasvluetzow @barbara_roessle @katha_schmid This is amazing

Фото профиля whatsupfranks

whatsupfranks3 месяцев назад

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

Фото профиля Kristian Calloway

Kristian Calloway1 месяц назад

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

Фото профиля Matthias Niessner

Matthias Niessner1 месяц назад

Just send me an email?

Фото профиля Sai Kiran Dev

Sai Kiran Dev3 месяцев назад

@nicolasvluetzow @barbara_roessle @katha_schmid Cool

Фото профиля ζ Pedram ζ

ζ Pedram ζ3 месяцев назад

@nicolasvluetzow @barbara_roessle @katha_schmid Nice

Фото профиля Nick Cassab

Nick Cassab3 месяцев назад

@nicolasvluetzow @barbara_roessle @katha_schmid Very cool

Фото профиля AI Mastery Guide

AI Mastery Guide3 месяцев назад

@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.

Фото профиля imaginary

imaginary3 месяцев назад

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.

Фото профиля goodtothinkwith

goodtothinkwith3 месяцев назад

@nicolasvluetzow @barbara_roessle @katha_schmid That is really cool

Фото профиля Geospatial FM

Geospatial FM3 месяцев назад

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

Похожие видео

📢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

📢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 просмотров • 6 месяцев назад

📢 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. 🔗 🌐 📄

📢 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

40,455 просмотров • 3 месяцев назад

📢📢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

📢📢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

18,420 просмотров • 4 месяцев назад

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!

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

15,185 просмотров • 1 месяц назад

📢 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!

📢 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 просмотров • 1 год назад

📢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 👇

📢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

42,986 просмотров • 3 месяцев назад

📢 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!

📢 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 просмотров • 10 месяцев назад

is it legal? NVIDIA and Microsoft just open-sourced the pieces of a full 3D studio for Opus 5.5 15 github repos, sorted by what you want to make: GENERATE 3D ASSETS 01. TRELLIS.2 by Microsoft: -> one image in, a fully textured 3D asset out, about 3 seconds on an H100 02. Hunyuan3D-2.1 by Tencent: -> production-ready 3D assets with PBR textures 03. stable-fast-3d by Stability AI: -> one photo to a clean UV-unwrapped mesh, built for speed 04. meshy-mcp-server by Meshy: -> text or image to 3D, then remesh, retexture, rig and animate from your agent BUILD SCENES AND WORLDS 05. mcp-for-blender: -> prompt-driven modeling, scene building and edits in a live Blender 06. HY-World-2.0 by Tencent: -> text or a single image to a navigable 3D world 07. supersplat by PlayCanvas: -> inspect, edit, optimize and publish 3D Gaussian splats in the browser 08. kit-usd-agents by NVIDIA: -> edit Omniverse USD scenes in plain English, plus MCP servers for Kit and Isaac Sim MAKE A GAME 09. unity-mcp: -> run the Unity Editor in plain English: scenes, C# scripts, assets, tests, builds 10. godot-ai: -> 46 tools for a live Godot editor: scenes, scripts, signals, UI, particles 11. unreal-engine-mcp: -> drive a live Unreal Editor: actors, world building, Blueprints 3D ON THE WEB 12. editor-mcp-server by PlayCanvas: -> your agent builds PlayCanvas scenes and checks they actually run 13. three.js: -> the JavaScript 3D library itself, 115k stars on GitHub 14. react-three-fiber: -> build three.js scenes as reusable React components 15. threejs-skills: -> 10 three.js skills for Claude Code, from shaders to post-processing a full 3D pipeline, and every piece of it lives on github

is it legal? NVIDIA and Microsoft just open-sourced the pieces of a full 3D studio for Opus 5.5 15 github repos, sorted by what you want to make: GENERATE 3D ASSETS 01. TRELLIS.2 by Microsoft: -> one image in, a fully textured 3D asset out, about 3 seconds on an H100 02. Hunyuan3D-2.1 by Tencent: -> production-ready 3D assets with PBR textures 03. stable-fast-3d by Stability AI: -> one photo to a clean UV-unwrapped mesh, built for speed 04. meshy-mcp-server by Meshy: -> text or image to 3D, then remesh, retexture, rig and animate from your agent BUILD SCENES AND WORLDS 05. mcp-for-blender: -> prompt-driven modeling, scene building and edits in a live Blender 06. HY-World-2.0 by Tencent: -> text or a single image to a navigable 3D world 07. supersplat by PlayCanvas: -> inspect, edit, optimize and publish 3D Gaussian splats in the browser 08. kit-usd-agents by NVIDIA: -> edit Omniverse USD scenes in plain English, plus MCP servers for Kit and Isaac Sim MAKE A GAME 09. unity-mcp: -> run the Unity Editor in plain English: scenes, C# scripts, assets, tests, builds 10. godot-ai: -> 46 tools for a live Godot editor: scenes, scripts, signals, UI, particles 11. unreal-engine-mcp: -> drive a live Unreal Editor: actors, world building, Blueprints 3D ON THE WEB 12. editor-mcp-server by PlayCanvas: -> your agent builds PlayCanvas scenes and checks they actually run 13. three.js: -> the JavaScript 3D library itself, 115k stars on GitHub 14. react-three-fiber: -> build three.js scenes as reusable React components 15. threejs-skills: -> 10 three.js skills for Claude Code, from shaders to post-processing a full 3D pipeline, and every piece of it lives on github

Mnimiy

205,109 просмотров • 6 дней назад

📢📢 𝐆𝐚𝐮𝐬𝐬𝐢𝐚𝐧𝐒𝐩𝐞𝐞𝐜𝐡: Audio-Driven Gaussian Avatars 📢📢 We synthesize photorealistic and 3D-consistent talking human head avatars driven directly from spoken audio. More specifically, we introduce an efficient 3DGS-based representation, combined with an audio-conditioned transformer, to generate realistic and high-quality animations. Our method can easily generalize to a variety of in the wild scenarios like songs, foreign languages etc. We further introduce a new multiview dataset of native English speakers with overall recording time of ∼3.5 hours. Project: Video: Great work by Shivangi, Artem Sevastopolsky, Tobias Kirschstein, Justus Thies, Angela Dai

📢📢 𝐆𝐚𝐮𝐬𝐬𝐢𝐚𝐧𝐒𝐩𝐞𝐞𝐜𝐡: Audio-Driven Gaussian Avatars 📢📢 We synthesize photorealistic and 3D-consistent talking human head avatars driven directly from spoken audio. More specifically, we introduce an efficient 3DGS-based representation, combined with an audio-conditioned transformer, to generate realistic and high-quality animations. Our method can easily generalize to a variety of in the wild scenarios like songs, foreign languages etc. We further introduce a new multiview dataset of native English speakers with overall recording time of ∼3.5 hours. Project: Video: Great work by Shivangi, Artem Sevastopolsky, Tobias Kirschstein, Justus Thies, Angela Dai

Matthias Niessner

22,703 просмотров • 1 год назад

📢📢 𝐏𝐞𝐫𝐜𝐇𝐞𝐚𝐝: 𝐏𝐞𝐫𝐜𝐞𝐩𝐭𝐮𝐚𝐥 𝐇𝐞𝐚𝐝 𝐌𝐨𝐝𝐞𝐥 𝐟𝐨𝐫 𝐒𝐢𝐧𝐠𝐥𝐞-𝐈𝐦𝐚𝐠𝐞 𝟑𝐃 𝐇𝐞𝐚𝐝 𝐑𝐞𝐜𝐨𝐧𝐬𝐭𝐫𝐮𝐜𝐭𝐢𝐨𝐧 & 𝐄𝐝𝐢𝐭𝐢𝐧𝐠📢📢 PercHead reconstructs realistic 3D heads from a single image and enables disentangled 3D editing via geometric controls and style inputs from images or text. At its core is a generalized 3D head decoder trained with perceptual supervision from DINOv2 and SAM 2.1. We find that our new perceptual loss formulation improves reconstruction fidelity compared to commonly-used methods such as LPIPS. Our trained reconstruction model is able to generate 3D-consistent heads from a single input image. Even with challenging side-view inputs, the model robustly infers missing regions for a coherent, high-fidelity output. In addition, our architecture seamlessly adapts to downstream tasks: by swapping the encoder, we can transform the model into a disentangled 3D editing pipeline. In this scenario, we can control geometry through - potentially hand-drawn - segmentation maps, and condition style via image or text prompt. We also provide an interactive GUI to enable the exploration of our editing pipeline. 🌍 📽️ Great work by Antonio Oroz and Tobias Kirschstein

📢📢 𝐏𝐞𝐫𝐜𝐇𝐞𝐚𝐝: 𝐏𝐞𝐫𝐜𝐞𝐩𝐭𝐮𝐚𝐥 𝐇𝐞𝐚𝐝 𝐌𝐨𝐝𝐞𝐥 𝐟𝐨𝐫 𝐒𝐢𝐧𝐠𝐥𝐞-𝐈𝐦𝐚𝐠𝐞 𝟑𝐃 𝐇𝐞𝐚𝐝 𝐑𝐞𝐜𝐨𝐧𝐬𝐭𝐫𝐮𝐜𝐭𝐢𝐨𝐧 & 𝐄𝐝𝐢𝐭𝐢𝐧𝐠📢📢 PercHead reconstructs realistic 3D heads from a single image and enables disentangled 3D editing via geometric controls and style inputs from images or text. At its core is a generalized 3D head decoder trained with perceptual supervision from DINOv2 and SAM 2.1. We find that our new perceptual loss formulation improves reconstruction fidelity compared to commonly-used methods such as LPIPS. Our trained reconstruction model is able to generate 3D-consistent heads from a single input image. Even with challenging side-view inputs, the model robustly infers missing regions for a coherent, high-fidelity output. In addition, our architecture seamlessly adapts to downstream tasks: by swapping the encoder, we can transform the model into a disentangled 3D editing pipeline. In this scenario, we can control geometry through - potentially hand-drawn - segmentation maps, and condition style via image or text prompt. We also provide an interactive GUI to enable the exploration of our editing pipeline. 🌍 📽️ Great work by Antonio Oroz and Tobias Kirschstein

Matthias Niessner

18,903 просмотров • 11 месяцев назад

⚡️ Discover What’s New on MetaTailor! New $NEURAL 3D assets are now available for game developers on METATAILOR. Whether you're designing levels, setting up scenes, or building a game from scratch, this drop adds more creative options to your toolkit. The latest release is powered by NeuralAI—explore it today. Start creating like a pro, sign up & subscribe today at 🚀

⚡️ Discover What’s New on MetaTailor! New $NEURAL 3D assets are now available for game developers on METATAILOR. Whether you're designing levels, setting up scenes, or building a game from scratch, this drop adds more creative options to your toolkit. The latest release is powered by NeuralAI—explore it today. Start creating like a pro, sign up & subscribe today at 🚀

RYFT CORP

41,389 просмотров • 1 год назад

📢WorldAgents: 3D worlds only from 2D image models - without any training! We propose an agentic approach with a Director (VLM) to plan the scene, a Generator (Flux or NanoBanana) for new views, and a Verifier (VLM) for selection / 3D consistency. -> High-fidelity 3D worlds from a single text prompt. What's remarkable: our agents find consistent views from 2D image models to obtain 3D-consistent worlds; this shows that image models contain world priors - agents just need to find them! Great work by Ziya Erkoç Angela Dai

📢WorldAgents: 3D worlds only from 2D image models - without any training! We propose an agentic approach with a Director (VLM) to plan the scene, a Generator (Flux or NanoBanana) for new views, and a Verifier (VLM) for selection / 3D consistency. -> High-fidelity 3D worlds from a single text prompt. What's remarkable: our agents find consistent views from 2D image models to obtain 3D-consistent worlds; this shows that image models contain world priors - agents just need to find them! Great work by Ziya Erkoç Angela Dai

Matthias Niessner

19,093 просмотров • 6 месяцев назад

🔥Excited to share the first released work from our IEI lab! Congrats to AnteaWu 🎉 This work is motivated by the lack of quantitative evaluation for physics alignment in video world models. With tools like MegaSam and CoTracker, we can directly reconstruct dynamic 3D scenes, enabling quantitative evaluation of physical alignment. Both code and data are released — feel free to try it out! It should work, but if it doesn’t, contact AnteaWu directly : )

🔥Excited to share the first released work from our IEI lab! Congrats to AnteaWu 🎉 This work is motivated by the lack of quantitative evaluation for physics alignment in video world models. With tools like MegaSam and CoTracker, we can directly reconstruct dynamic 3D scenes, enabling quantitative evaluation of physical alignment. Both code and data are released — feel free to try it out! It should work, but if it doesn’t, contact AnteaWu directly : )

Xueyan Zou

10,239 просмотров • 5 месяцев назад

📢📢 𝐀𝐯𝐚𝐭𝟑𝐫 📢📢 Avat3r creates high-quality 3D head avatars from just a few input images in a single forward pass with a new dynamic 3DGS reconstruction model. Video: Project: Our core idea is to make Gaussian Reconstruction Models animatable. We find that a simple cross-attention to an expression code sequence is already sufficient to model complex facial expressions. We then incorporate position maps from DUSt3R and feature maps from Sapiens to facilitate the prediction task. While DUSt3R's position maps act as a pixel-aligned initialization for the Gaussians' positions, the Sapiens feature maps help the cross-view transformer to match corresponding image tokens in the 4 input images. One major challenge in creating a 3D head avatar from smartphone images comes from inconsistent facial expressions when the subject could not remain perfectly static during the capture. We eliminate this static requirement by simply showing our model input images with different facial expressions during training. This technique makes our model robust to inconsistent input images later on. Finally, we show that despite the model has been trained with 4 input images, one can even create a 3D head avatar when only a single image is available. To achieve this, we employ a pre-trained 3D GAN to lift the single image to 3D and then render the 4 input images for our model. This allows us to create 3D head avatars from single images and even highly out-of-distribution examples like AI generated faces, paintings or statues. Great work by Tobias Kirschstein from his internship at Meta with Javier Romero, Artem Sevastopolsky, and Shunsuke Saito

Matthias Niessner

74,863 просмотров • 1 год назад

building large language models from scratch by Sebastian Raschka was a great chance for me to sit down and study again all the LLM basics > token and positional embeddings > self-attention and what QKV is about > causal & multi-head attention studying llms and how they work can seem overwhelming at first. but once you taste how good it feels to learn these things intuitively there's no going back. I shared the resources and my notes on my repo and I hope it's a motivation if you want to start as well or recap.

building large language models from scratch by Sebastian Raschka was a great chance for me to sit down and study again all the LLM basics > token and positional embeddings > self-attention and what QKV is about > causal & multi-head attention studying llms and how they work can seem overwhelming at first. but once you taste how good it feels to learn these things intuitively there's no going back. I shared the resources and my notes on my repo and I hope it's a motivation if you want to start as well or recap.

ℏεsam

49,635 просмотров • 1 год назад

📢 OneCanvas: 3D Scene Understanding via Panoramic Reprojection We extract features from video frames and reproject them into one occlusion-free view of the whole scene that a 2D VLM reads just like a normal image. We can center this view on any viewpoint, including an agent's own pose for situated reasoning. The same projection lets us create spatial training tasks with no human annotation, solvable only by reasoning over the 3D positions of real object features placed on an otherwise empty canvas. The result is a stock 2D VLM that reasons in 3D, setting a new state of the art across spatial benchmarks at far less compute. 🌐 ▶️ Great work by Bartłomiej Baranowski & Dave Zhenyu Chen

📢 OneCanvas: 3D Scene Understanding via Panoramic Reprojection We extract features from video frames and reproject them into one occlusion-free view of the whole scene that a 2D VLM reads just like a normal image. We can center this view on any viewpoint, including an agent's own pose for situated reasoning. The same projection lets us create spatial training tasks with no human annotation, solvable only by reasoning over the 3D positions of real object features placed on an otherwise empty canvas. The result is a stock 2D VLM that reasons in 3D, setting a new state of the art across spatial benchmarks at far less compute. 🌐 ▶️ Great work by Bartłomiej Baranowski & Dave Zhenyu Chen

Matthias Niessner

42,559 просмотров • 4 месяцев назад

Hyper3D just launched WorldGen, and it takes 3D generation from single assets to full scenes. From one image, it builds a structured 3D scene where every important object is its own editable asset. You can move it, replace it, edit it, and interact with it. How it works: 1. Upload a scene image 2. WorldGen identifies the objects 3. Generate the full scene with Max Gen and walk around with WASD 4. Select any object and move, delete, replace, or regenerate it with Hyper3D Rodin 5. Click "Interactive" to see physical properties 6. Export to Blender, Unity, or UE It pairs Rodin's independent Mesh assets with 3D Gaussian Splatting for the environment, and predicts position, scale, collision, mass, and friction. Built for embodied AI training, film pre-viz with video models like Seedance 2.5, game dev, and XR. From DeemosTech, whose CAST research won a Best Paper Award at SIGGRAPH 2025. Try Hyper3D WorldGen: Get updates Hyper3D by Deemos: 14-day Free Trial Code: 35TLO1MS #Hyper3D #DeemosTech #Rodin #WorldGen #AI3D

Hyper3D just launched WorldGen, and it takes 3D generation from single assets to full scenes. From one image, it builds a structured 3D scene where every important object is its own editable asset. You can move it, replace it, edit it, and interact with it. How it works: 1. Upload a scene image 2. WorldGen identifies the objects 3. Generate the full scene with Max Gen and walk around with WASD 4. Select any object and move, delete, replace, or regenerate it with Hyper3D Rodin 5. Click "Interactive" to see physical properties 6. Export to Blender, Unity, or UE It pairs Rodin's independent Mesh assets with 3D Gaussian Splatting for the environment, and predicts position, scale, collision, mass, and friction. Built for embodied AI training, film pre-viz with video models like Seedance 2.5, game dev, and XR. From DeemosTech, whose CAST research won a Best Paper Award at SIGGRAPH 2025. Try Hyper3D WorldGen: Get updates Hyper3D by Deemos: 14-day Free Trial Code: 35TLO1MS #Hyper3D #DeemosTech #Rodin #WorldGen #AI3D

LX™

92,219 просмотров • 19 дней назад

Exploring 3D Generation Capabilities in Alchemist AI🔮 Alchemist AI now enables users to create basic 3D assets, including models, objects, environments, and simulations, expanding its capabilities beyond 2D asset generation. What Does This Mean for You? • 3D Environment Creation: Generate virtual worlds, such as game environments or fantasy landscapes. Define parameters like terrain or structures to create dynamic and adaptable spaces tailored to your needs. • Customizable 3D Models and Objects: Design and modify 3D assets by adjusting dimensions, materials, and textures. Whether crafting prototypes or characters, users maintain full creative control. • Interactive Simulations: Build physics-based simulations or animated scenes. With upcoming support for sprite libraries and animation rigs, fine-tune object behaviors and interactions to suit your projects. With future API updates, Alchemist AI’s 3D generation capabilities will further expand, enhancing tools for creating models, environments, and simulations. AI-assisted text-to-3D will also be introduced—just describe your vision, such as 'space station' or 'orange sports car' and the system will generate customizable base assets.

Exploring 3D Generation Capabilities in Alchemist AI🔮 Alchemist AI now enables users to create basic 3D assets, including models, objects, environments, and simulations, expanding its capabilities beyond 2D asset generation. What Does This Mean for You? • 3D Environment Creation: Generate virtual worlds, such as game environments or fantasy landscapes. Define parameters like terrain or structures to create dynamic and adaptable spaces tailored to your needs. • Customizable 3D Models and Objects: Design and modify 3D assets by adjusting dimensions, materials, and textures. Whether crafting prototypes or characters, users maintain full creative control. • Interactive Simulations: Build physics-based simulations or animated scenes. With upcoming support for sprite libraries and animation rigs, fine-tune object behaviors and interactions to suit your projects. With future API updates, Alchemist AI’s 3D generation capabilities will further expand, enhancing tools for creating models, environments, and simulations. AI-assisted text-to-3D will also be introduced—just describe your vision, such as 'space station' or 'orange sports car' and the system will generate customizable base assets.

ALCHEMIST AI 🔮

35,673 просмотров • 1 год назад

Introducing Hedra Elements. Elements lets you build scenes by combining reusable components—visually and through prompts—so you can generate consistent, remixable content at speed. Pick from our library or upload your own elements (characters, outfits, style, location) and reference them directly in prompts with tags. Stop building from scratch every time. Start creating faster and smarter. We're giving the first 100 followers who reply “HEDRA ELEMENTS” a full month of Hedra FREE. I’ll DM the code. Ready when you are.

Introducing Hedra Elements. Elements lets you build scenes by combining reusable components—visually and through prompts—so you can generate consistent, remixable content at speed. Pick from our library or upload your own elements (characters, outfits, style, location) and reference them directly in prompts with tags. Stop building from scratch every time. Start creating faster and smarter. We're giving the first 100 followers who reply “HEDRA ELEMENTS” a full month of Hedra FREE. I’ll DM the code. Ready when you are.

Hedra

831,532 просмотров • 9 месяцев назад

My ideas used to stay stuck at the script stage. Writing scenes was easy, but turning them into actual animated shots always felt heavy. Too many tools. Too much technical friction. The story would lose momentum halfway through. That changed when I spent time exploring CineV | 3D-Controlled AI Animation. What clicked for me was how it starts from a story, not a timeline or a blank canvas. You write first, then it builds a storyboard around that idea. From there, you can review shots, regenerate scenes, adjust expressions, tweak camera angles, and refine motion instead of accepting one random output. I found myself thinking more like a director than a prompt engineer. Choosing what shots worked, pacing scenes, and polishing moments without needing to animate everything from scratch. Less friction. Fewer compromises. More control over the final result. What stood out next was the flexibility. There’s a faster text to video flow when speed matters, and a more hands on storyboard and 3D edit mode when you care about camera work and continuity. You decide how deep you want to go. It still feels early and very creator focused, but the full workflow from script to export is already there. CineV feels less like a clip generator and more like a storytelling tool for anime style animation. Worth a look if you work with narrative ideas and want them to actually turn into finished scenes. Try it here:

My ideas used to stay stuck at the script stage. Writing scenes was easy, but turning them into actual animated shots always felt heavy. Too many tools. Too much technical friction. The story would lose momentum halfway through. That changed when I spent time exploring CineV | 3D-Controlled AI Animation. What clicked for me was how it starts from a story, not a timeline or a blank canvas. You write first, then it builds a storyboard around that idea. From there, you can review shots, regenerate scenes, adjust expressions, tweak camera angles, and refine motion instead of accepting one random output. I found myself thinking more like a director than a prompt engineer. Choosing what shots worked, pacing scenes, and polishing moments without needing to animate everything from scratch. Less friction. Fewer compromises. More control over the final result. What stood out next was the flexibility. There’s a faster text to video flow when speed matters, and a more hands on storyboard and 3D edit mode when you care about camera work and continuity. You decide how deep you want to go. It still feels early and very creator focused, but the full workflow from script to export is already there. CineV feels less like a clip generator and more like a storytelling tool for anime style animation. Worth a look if you work with narrative ideas and want them to actually turn into finished scenes. Try it here:

FELIX

122,203 просмотров • 9 месяцев назад