Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

(1/2) Check out 𝐌𝐞𝐬𝐡𝐆𝐏𝐓! MeshGPT generates triangle meshes by autoregressively sampling from a transformer model that produces tokens from a learned geometric vocabulary. As a result, we obtain clean and compact meshes :)

Matthias Niessner

48,649 subscribers

396,324 views • 2 years ago •via X (Twitter)

Education Science & Technology

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

(1/2) Check out "𝐏𝐨𝐥𝐲𝐃𝐢𝐟𝐟: Generating 3D Polygonal Meshes with Diffusion Models"! Our model operates directly on the polygons of 3D meshes and generates novel shapes as output through an iterative diffusion process.

(1/2) Check out "𝐏𝐨𝐥𝐲𝐃𝐢𝐟𝐟: Generating 3D Polygonal Meshes with Diffusion Models"! Our model operates directly on the polygons of 3D meshes and generates novel shapes as output through an iterative diffusion process.

Matthias Niessner

57,947 views • 2 years ago

We got it first - now it’s yours to play with. Scenario integrates Tencent Hy acclaimed model... HUNYUAN 3D 3.0 Clean, game-ready 3D meshes, from a single image or sketch. 👇👇

We got it first - now it’s yours to play with. Scenario integrates Tencent Hy acclaimed model... HUNYUAN 3D 3.0 Clean, game-ready 3D meshes, from a single image or sketch. 👇👇

Emm | scenario.com

57,599 views • 8 months ago

Check out Easy Envelope, a new add-on for Blender that allows you to easily weight meshes with complex structures, such as cloaks, multi-layered skirts, and hair composed of meshes. Learn more and download: #blender #blender3d #b3d #gamedev #3d #3dart

Check out Easy Envelope, a new add-on for Blender that allows you to easily weight meshes with complex structures, such as cloaks, multi-layered skirts, and hair composed of meshes. Learn more and download: #blender #blender3d #b3d #gamedev #3d #3dart

80 LEVEL

51,229 views • 2 years ago

Echo-2 is a physically-grounded world model from which we can distill meshes, point clouds, or 3DGS scene representations. Directly usable in a myriad of downstream applications from gaming to training robots. Want to build your own world? Try it here:

Echo-2 is a physically-grounded world model from which we can distill meshes, point clouds, or 3DGS scene representations. Directly usable in a myriad of downstream applications from gaming to training robots. Want to build your own world? Try it here:

SpAItial AI

21,416 views • 3 months ago

(1/2) MonoNPHM will be presented as a #CVPR2024 Highlight! Our Neural Parametric Head Model parametrizes both geometry and appearance. With the learned model, we can then 3D reconstruct and track human heads from images or videos.

(1/2) MonoNPHM will be presented as a #CVPR2024 Highlight! Our Neural Parametric Head Model parametrizes both geometry and appearance. With the learned model, we can then 3D reconstruct and track human heads from images or videos.

Matthias Niessner

17,209 views • 2 years ago

ImmerseGen: Agent-Guided Immersive World Generation with Alpha-Textured Proxies Contributions: 1) We propose ImmerseGen, a novel agent-guided 3D environment generation framework. It uses simplified geometric proxies with alpha-textured meshes to produce compact, photorealistic worlds ready for real-time mobile VR rendering. 2) We propose a novel RGBA texturing paradigm. It first synthesizes 8K terrain textures using a geometry-conditioned panorama generator via user-centric mapping, and then directly generates alpha-textured proxy assets, avoiding fidelity loss typically resulting from mesh decimation. 3) To automate scene creation from user prompts, we introduce VLM-based modeling agents equipped with a novel grid-based semantic analysis. This enables 3D spatial reasoning from 2D observations and ensures accurate asset placement. ImmerseGen further enhances immersion with dynamic effects and ambient audio for a multisensory experience. 4) Experiments on multiple scene-generation scenarios and live mobile VR applications show that ImmerseGen outperforms previous methods in visual quality, realism, spatial coherence, and rendering efficiency for immersive real-time VR experiences.

ImmerseGen: Agent-Guided Immersive World Generation with Alpha-Textured Proxies Contributions: 1) We propose ImmerseGen, a novel agent-guided 3D environment generation framework. It uses simplified geometric proxies with alpha-textured meshes to produce compact, photorealistic worlds ready for real-time mobile VR rendering. 2) We propose a novel RGBA texturing paradigm. It first synthesizes 8K terrain textures using a geometry-conditioned panorama generator via user-centric mapping, and then directly generates alpha-textured proxy assets, avoiding fidelity loss typically resulting from mesh decimation. 3) To automate scene creation from user prompts, we introduce VLM-based modeling agents equipped with a novel grid-based semantic analysis. This enables 3D spatial reasoning from 2D observations and ensures accurate asset placement. ImmerseGen further enhances immersion with dynamic effects and ambient audio for a multisensory experience. 4) Experiments on multiple scene-generation scenarios and live mobile VR applications show that ImmerseGen outperforms previous methods in visual quality, realism, spatial coherence, and rendering efficiency for immersive real-time VR experiences.

MrNeRF

14,225 views • 1 year ago

Fuck yeah! MaskGCT - New open SoTA Text to Speech model! 🔥 > Zero-shot voice cloning > Emotional TTS > Trained on 100K hours of data > Long form synthesis > Variable speed synthesis > Bilingual - Chinese & English > Available on Hugging Face Fully non-autoregressive architecture: > Stage 1: Predicts semantic tokens from text, using tokens extracted from a speech self-supervised learning (SSL) model > Stage 2: Predicts acoustic tokens conditioned on the semantic tokens. Synthesised: "Would you guys personally like to have a fake fireplace, an electric one, in your house? Or would you rather have a real fireplace? Let me know down below. Okay everybody, that's all for today's video and I hope you guys learned a bunch of furniture vocabulary!" TTS scene keeps getting lit! 🐐

Fuck yeah! MaskGCT - New open SoTA Text to Speech model! 🔥 > Zero-shot voice cloning > Emotional TTS > Trained on 100K hours of data > Long form synthesis > Variable speed synthesis > Bilingual - Chinese & English > Available on Hugging Face Fully non-autoregressive architecture: > Stage 1: Predicts semantic tokens from text, using tokens extracted from a speech self-supervised learning (SSL) model > Stage 2: Predicts acoustic tokens conditioned on the semantic tokens. Synthesised: "Would you guys personally like to have a fake fireplace, an electric one, in your house? Or would you rather have a real fireplace? Let me know down below. Okay everybody, that's all for today's video and I hope you guys learned a bunch of furniture vocabulary!" TTS scene keeps getting lit! 🐐

Vaibhav (VB) Srivastav

139,105 views • 1 year ago

Goalpara, Karbi Anglong and Cachar- I’ve been sampling pineapples from across Assam. The Cachar variant from yesterday stood out for its tangy flavour and a zero-waste circular farming model. We’re already India’s 2nd largest pineapple producer. We’re coming for No. 1.

Goalpara, Karbi Anglong and Cachar- I’ve been sampling pineapples from across Assam. The Cachar variant from yesterday stood out for its tangy flavour and a zero-waste circular farming model. We’re already India’s 2nd largest pineapple producer. We’re coming for No. 1.

Himanta Biswa Sarma

32,438 views • 20 days ago

(1/2) Check out 𝐆𝐚𝐮𝐬𝐬𝐢𝐚𝐧𝐀𝐯𝐚𝐭𝐚𝐫𝐬: Photorealistic Head Avatars with Rigged 3D Gaussians! We create photorealistic head avatars by animating 3D Gaussians on a parametric face model - edited and rendered in *real-time*!

(1/2) Check out 𝐆𝐚𝐮𝐬𝐬𝐢𝐚𝐧𝐀𝐯𝐚𝐭𝐚𝐫𝐬: Photorealistic Head Avatars with Rigged 3D Gaussians! We create photorealistic head avatars by animating 3D Gaussians on a parametric face model - edited and rendered in real-time!

Matthias Niessner

127,015 views • 2 years ago

🔥 2 BILLION $ATLA BURNED 🔥 Major milestone for the ATLA ecosystem. 2 BILLION tokens permanently removed from supply — cutting total allocation by nearly 2/3. 👇 Why it happened As ATLA demand and value grew, the team reviewed the original token allocation and decided to burn a large portion of undistributed tokens to strengthen the long-term token model. ⚠️ Important: This burn only affects undistributed tokens — current holders are not affected. Result: 📉 Lower future supply 📈 Stronger price fundamentals This makes $ATLA a much more limited and stronger asset🚀

🔥 2 BILLION $ATLA BURNED 🔥 Major milestone for the ATLA ecosystem. 2 BILLION tokens permanently removed from supply — cutting total allocation by nearly 2/3. 👇 Why it happened As ATLA demand and value grew, the team reviewed the original token allocation and decided to burn a large portion of undistributed tokens to strengthen the long-term token model. ⚠️ Important: This burn only affects undistributed tokens — current holders are not affected. Result: 📉 Lower future supply 📈 Stronger price fundamentals This makes $ATLA a much more limited and stronger asset🚀

Atleta Network

144,786 views • 4 months ago

Hamiltonian Monte Carlo frames sampling from a probability distribution as a physics problem. By endowing "particles" with momentum and simulating their energy and motion through Hamilton's equations you can efficiently explore a distribution.

Hamiltonian Monte Carlo frames sampling from a probability distribution as a physics problem. By endowing "particles" with momentum and simulating their energy and motion through Hamilton's equations you can efficiently explore a distribution.

Alec Helbling

168,671 views • 8 months ago

We took a 30B model and split it in two to write tokens in parallel instead of one at a time. Introducing Nemotron-Labs-TwoTower: a diffusion language model from NVIDIA Research adapted from Nemotron-3-Nano-30B-A3B. Here’s how it works: one half holds the context, the other writes the tokens, with both reusing the pretrained model instead of training a new one from scratch. We found it kept 98.7% of the original model’s quality at 2.42× faster generation.

We took a 30B model and split it in two to write tokens in parallel instead of one at a time. Introducing Nemotron-Labs-TwoTower: a diffusion language model from NVIDIA Research adapted from Nemotron-3-Nano-30B-A3B. Here’s how it works: one half holds the context, the other writes the tokens, with both reusing the pretrained model instead of training a new one from scratch. We found it kept 98.7% of the original model’s quality at 2.42× faster generation.

NVIDIA AI

759,488 views • 1 month ago

(1/2) Intrinsic Image Diffusion for Single-view Material Estimation! We propose a probabilistic diffusion model to handle material & lighting ambiguities. We obtain sharp material estimates and facilitate high-fidelity relighting.

(1/2) Intrinsic Image Diffusion for Single-view Material Estimation! We propose a probabilistic diffusion model to handle material & lighting ambiguities. We obtain sharp material estimates and facilitate high-fidelity relighting.

Matthias Niessner

69,400 views • 2 years ago

We cooked and we fully built out a native Swift app from Burke Holland's awesome resize me and it totally worked with a 1 shot after advanced planning! Some deep insight from Pierce Boggan as always

We cooked and we fully built out a native Swift app from Burke Holland's awesome resize me and it totally worked with a 1 shot after advanced planning! Some deep insight from Pierce Boggan as always

James Montemagno

16,859 views • 1 month ago

Greptile just got a brand refresh done entirely in-house. we pulled inspiration from moments in the past that once felt futuristic, from the terminal to video games, 80s malls, neon genesis, and of course reptiles, their repeating scales, and their colorful environments. the result is a diverse color palette, intricate illustrations, and modular geometric forms that feel complex yet precise and ethereal. 🧵the process and thinking below:

Ravina Patel

19,641 views • 3 months ago

Many 3D generators output Gaussian Splats (3DGS) for fast rendering, flexible deployment, and high visual fidelity. Static 3DGS aren't world models (no dynamics/semantics) but a true world model must allow distilling 3D-consistent representations for any given time step (3DGS/meshes). This post-distillation serves a dual purpose: 1) validates physical consistency of the model. 2) extracting explicit representations avoids continuously running a heavy generator, thus saves compute and facilitates real-time interaction.

Many 3D generators output Gaussian Splats (3DGS) for fast rendering, flexible deployment, and high visual fidelity. Static 3DGS aren't world models (no dynamics/semantics) but a true world model must allow distilling 3D-consistent representations for any given time step (3DGS/meshes). This post-distillation serves a dual purpose: 1) validates physical consistency of the model. 2) extracting explicit representations avoids continuously running a heavy generator, thus saves compute and facilitates real-time interaction.

Matthias Niessner

26,416 views • 4 months ago

Open UI Local 1 Click Launcher Open UI from wan deeee bee is a cool AI app that live-generates UIs. It's like Vercel's V0 but open source, and works with both ChatGPT & open source models via ollama Make sure to check out Matthew Berman's tutorial, and run it with 1 click.

Open UI Local 1 Click Launcher Open UI from wan deeee bee is a cool AI app that live-generates UIs. It's like Vercel's V0 but open source, and works with both ChatGPT & open source models via ollama Make sure to check out Matthew Berman's tutorial, and run it with 1 click.

cocktail peanut

53,965 views • 2 years ago

Last week we released our Gemini 3.1 Pro Deep Think model. Here are a succession of examples of that model doing heat transfer analysis. No tools, just Deep Think and Image Generation. Step 1: generate a CAD file from a technical drawing.

Last week we released our Gemini 3.1 Pro Deep Think model. Here are a succession of examples of that model doing heat transfer analysis. No tools, just Deep Think and Image Generation. Step 1: generate a CAD file from a technical drawing.

Jeff Dean

154,245 views • 5 months ago

The Hidden Language of Diffusion Models paper page: tackle the challenge of understanding concept representations in text-to-image models by decomposing an input text prompt into a small set of interpretable elements. This is achieved by learning a pseudo-token that is a sparse weighted combination of tokens from the model's vocabulary, with the objective of reconstructing the images generated for the given concept. Applied over the state-of-the-art Stable Diffusion model, this decomposition reveals non-trivial and surprising structures in the representations of concepts. For example, we find that some concepts such as "a president" or "a composer" are dominated by specific instances (e.g., "Obama", "Biden") and their interpolations. Other concepts, such as "happiness" combine associated terms that can be concrete ("family", "laughter") or abstract ("friendship", "emotion"). In addition to peering into the inner workings of Stable Diffusion, our method also enables applications such as single-image decomposition to tokens, bias detection and mitigation, and semantic image manipulation

The Hidden Language of Diffusion Models paper page: tackle the challenge of understanding concept representations in text-to-image models by decomposing an input text prompt into a small set of interpretable elements. This is achieved by learning a pseudo-token that is a sparse weighted combination of tokens from the model's vocabulary, with the objective of reconstructing the images generated for the given concept. Applied over the state-of-the-art Stable Diffusion model, this decomposition reveals non-trivial and surprising structures in the representations of concepts. For example, we find that some concepts such as "a president" or "a composer" are dominated by specific instances (e.g., "Obama", "Biden") and their interpolations. Other concepts, such as "happiness" combine associated terms that can be concrete ("family", "laughter") or abstract ("friendship", "emotion"). In addition to peering into the inner workings of Stable Diffusion, our method also enables applications such as single-image decomposition to tokens, bias detection and mitigation, and semantic image manipulation

AK

41,746 views • 3 years ago

For the head angle, I learn from @ cillia new rigging file so check it out link below, it's super helpful and I learned a lot! #Vtuber #Live2d

For the head angle, I learn from @ cillia new rigging file so check it out link below, it's super helpful and I learned a lot! #Vtuber #Live2d

💕 Noiri ┆Live2D

81,571 views • 1 year ago