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

Introducing Objaverse-XL, an open dataset of over 10 million 3D objects! With it, we train Zero123-XL, a foundation model for 3D, observing incredible 3D generalization abilities: 🧵👇 📝 Paper:

Matt Deitke

13,565 subscribers

368,704 просмотров • 3 лет назад •via X (Twitter)

Наука и технологии

Anya Rossi• Live Now

Private livecam show

Комментарии: 10

Фото профиля Matt Deitke

Matt Deitke3 лет назад

Objaverse 1.0 was released back in December. It was a step in the right direction, but still relatively small with 800K objects. Objaverse-XL is over an order of magnitude larger and much more diverse!

Фото профиля Matt Deitke

Matt Deitke3 лет назад

Compared to the original Zero123 model, Zero123-XL improves remarkably in 0-shot generalization abilities, even being able to perform novel view synthesis on sketches, cartoons, and people! A ton more examples in the paper :)

Фото профиля Matt Deitke

Matt Deitke3 лет назад

With the base Zero123-XL foundation model, we can perform image → 3D using DreamFusion, having the model guide a NeRF to generate novel views!

Фото профиля Matt Deitke

Matt Deitke3 лет назад

Text-to-3D comes for free with text → image models, such as with SDXL here, providing the initial image!

Фото профиля Matt Deitke

Matt Deitke3 лет назад

Beyond that, we show strong scaling trends for both Zero123-XL and PixelNeRF!

Фото профиля Matt Deitke

Matt Deitke3 лет назад

The data, code, and models will be openly available soon! 🤗 We’re thrilled to see what you build!

Фото профиля Matt Deitke

Matt Deitke3 лет назад

Objaverse-XL was a tremendously enjoyable collaboration between researchers at a bunch of organizations, including @allen_ai, Columbia University, @uwcse, @StabilityAI, @laion_ai, and Caltech. Compute for the experiments was generously provided by @StabilityAI!

Фото профиля Matt Deitke

Matt Deitke3 лет назад

It was an incredibly fun collaboration with the team, including @ruoshi_liu, Matthew Wallingford, @hvngo2002, Oscar Michel, @adityakusupati, @a1anfan, @chrlaf, @VikramVoleti, @sy_gadre, Eli VanderBilt, @anikembhavi, @cvondrick, @georgiagkioxari, @ehsanik, @lschmidt3, Ali Farhadi

Фото профиля Chris Heinrich

Chris Heinrich3 лет назад

Hey Matt, congrats on the work. However the savable content on Polycam is intended for our users, not for bots, and scraping is in violation of our Terms of Service. Sent you an email about this, please get back to me today.

Фото профиля Miaru3d →🍡 Commisions Open🍡

Miaru3d →🍡 Commisions Open🍡3 лет назад

I will invoice your for using my 3d models for your project, full price.

Похожие видео

One of the Top 5 most valuable companies in the world has just acquired a license for Over the Reality 3D mapping dataset to train next-generation vision foundation models. This is a huge milestone for OVER 🧵👇

One of the Top 5 most valuable companies in the world has just acquired a license for Over the Reality 3D mapping dataset to train next-generation vision foundation models. This is a huge milestone for OVER 🧵👇

Over the Reality 🌐

830,317 просмотров • 4 месяцев назад

Introducing Meta Locate 3D: a model for accurate object localization in 3D environments. Learn how Meta Locate 3D can help robots accurately understand their surroundings and interact more naturally with humans. You can download the model and dataset, read our research paper, and even try a demo!

Introducing Meta Locate 3D: a model for accurate object localization in 3D environments. Learn how Meta Locate 3D can help robots accurately understand their surroundings and interact more naturally with humans. You can download the model and dataset, read our research paper, and even try a demo!

AI at Meta

81,406 просмотров • 1 год назад

⚙️ 404—GEN has released the WORLD'S LARGEST open-source 3D model dataset ⚙️ • 21.5M+ AI-generated 3d models • Open-source and attribution-ready • Larger than all existing 3D datasets combined This is an unmatched scale for Gaussian Splatting research. More details below 🧵 ⬇️

⚙️ 404—GEN has released the WORLD'S LARGEST open-source 3D model dataset ⚙️ • 21.5M+ AI-generated 3d models • Open-source and attribution-ready • Larger than all existing 3D datasets combined This is an unmatched scale for Gaussian Splatting research. More details below 🧵 ⬇️

404

44,735 просмотров • 1 год назад

3DTopia-XL High-Quality 3D PBR Asset Generation via Primitive Diffusion demo: model: 3DTopia-XL scales high-quality 3D asset generation using Diffusion Transformer (DiT) built upon an expressive and efficient 3D representation, PrimX. The denoising process takes 5 seconds to generate a 3D PBR asset from text/image input which is ready for the graphics pipeline to use.

3DTopia-XL High-Quality 3D PBR Asset Generation via Primitive Diffusion demo: model: 3DTopia-XL scales high-quality 3D asset generation using Diffusion Transformer (DiT) built upon an expressive and efficient 3D representation, PrimX. The denoising process takes 5 seconds to generate a 3D PBR asset from text/image input which is ready for the graphics pipeline to use.

AK

87,282 просмотров • 1 год назад

Introducing Substance 3D Viewer (beta) a new 3D desktop app that can open, view, and render 70+ file formats. In Adobe Photoshop (beta), drag & drop a 3D model on your canvas, and it becomes an editable Smart Object. Download it for free and give it a try!

Introducing Substance 3D Viewer (beta) a new 3D desktop app that can open, view, and render 70+ file formats. In Adobe Photoshop (beta), drag & drop a 3D model on your canvas, and it becomes an editable Smart Object. Download it for free and give it a try!

Adobe Substance 3D

89,177 просмотров • 1 год назад

EgoLifter Open-world 3D Segmentation for Egocentric Perception In this paper we present EgoLifter, a novel system that can automatically segment scenes captured from egocentric sensors into a complete decomposition of individual 3D objects. The system is specifically

EgoLifter Open-world 3D Segmentation for Egocentric Perception In this paper we present EgoLifter, a novel system that can automatically segment scenes captured from egocentric sensors into a complete decomposition of individual 3D objects. The system is specifically

AK

41,117 просмотров • 2 лет назад

What happens when VLMs meet 3D foundation models? See VLM-3R (CVPR 2026). VLM-3R links a vision-language model (e.g., Qwen) with 3D geometric foundation models (e.g., CUT3R) at metric scale. Given an uncalibrated video, it moves beyond pixels to perceive and reason in 3D space. Code (open source):

What happens when VLMs meet 3D foundation models? See VLM-3R (CVPR 2026). VLM-3R links a vision-language model (e.g., Qwen) with 3D geometric foundation models (e.g., CUT3R) at metric scale. Given an uncalibrated video, it moves beyond pixels to perceive and reason in 3D space. Code (open source):

Zhiwen(Aaron) Fan

10,641 просмотров • 4 месяцев назад

How to harness foundation models for *generalization in the wild* in robot manipulation? Introducing VoxPoser: use LLM+VLM to label affordances and constraints directly in 3D perceptual space for zero-shot robot manipulation in the real world! 🌐 🧵👇

How to harness foundation models for generalization in the wild in robot manipulation? Introducing VoxPoser: use LLM+VLM to label affordances and constraints directly in 3D perceptual space for zero-shot robot manipulation in the real world! 🌐 🧵👇

Wenlong Huang

293,876 просмотров • 3 лет назад

DreamCraft3D: Hierarchical 3D Generation with Bootstrapped Diffusion Prior paper page: present DreamCraft3D, a hierarchical 3D content generation method that produces high-fidelity and coherent 3D objects. We tackle the problem by leveraging a 2D reference image to guide the stages of geometry sculpting and texture boosting. A central focus of this work is to address the consistency issue that existing works encounter. To sculpt geometries that render coherently, we perform score distillation sampling via a view-dependent diffusion model. This 3D prior, alongside several training strategies, prioritizes the geometry consistency but compromises the texture fidelity. We further propose Bootstrapped Score Distillation to specifically boost the texture. We train a personalized diffusion model, Dreambooth, on the augmented renderings of the scene, imbuing it with 3D knowledge of the scene being optimized. The score distillation from this 3D-aware diffusion prior provides view-consistent guidance for the scene. Notably, through an alternating optimization of the diffusion prior and 3D scene representation, we achieve mutually reinforcing improvements: the optimized 3D scene aids in training the scene-specific diffusion model, which offers increasingly view-consistent guidance for 3D optimization. The optimization is thus bootstrapped and leads to substantial texture boosting. With tailored 3D priors throughout the hierarchical generation, DreamCraft3D generates coherent 3D objects with photorealistic renderings, advancing the state-of-the-art in 3D content generation.

DreamCraft3D: Hierarchical 3D Generation with Bootstrapped Diffusion Prior paper page: present DreamCraft3D, a hierarchical 3D content generation method that produces high-fidelity and coherent 3D objects. We tackle the problem by leveraging a 2D reference image to guide the stages of geometry sculpting and texture boosting. A central focus of this work is to address the consistency issue that existing works encounter. To sculpt geometries that render coherently, we perform score distillation sampling via a view-dependent diffusion model. This 3D prior, alongside several training strategies, prioritizes the geometry consistency but compromises the texture fidelity. We further propose Bootstrapped Score Distillation to specifically boost the texture. We train a personalized diffusion model, Dreambooth, on the augmented renderings of the scene, imbuing it with 3D knowledge of the scene being optimized. The score distillation from this 3D-aware diffusion prior provides view-consistent guidance for the scene. Notably, through an alternating optimization of the diffusion prior and 3D scene representation, we achieve mutually reinforcing improvements: the optimized 3D scene aids in training the scene-specific diffusion model, which offers increasingly view-consistent guidance for 3D optimization. The optimization is thus bootstrapped and leads to substantial texture boosting. With tailored 3D priors throughout the hierarchical generation, DreamCraft3D generates coherent 3D objects with photorealistic renderings, advancing the state-of-the-art in 3D content generation.

AK

161,530 просмотров • 2 лет назад

We trained a foundation model on 18 million heart ultrasound videos to predict structure instead of pixels. Introducing EchoJEPA, the first foundation-scale JEPA for medical video. Paper: Code: 🧵 1/n

We trained a foundation model on 18 million heart ultrasound videos to predict structure instead of pixels. Introducing EchoJEPA, the first foundation-scale JEPA for medical video. Paper: Code: 🧵 1/n

Alif Munim (d/acc)

590,564 просмотров • 5 месяцев назад

👇Draw a sketch. Get a 3D model. Use it anywhere. Today, we're launching the Cursor + Midjourney for 3D modeling. This is Vibe Draw, the future of 3D creation:

👇Draw a sketch. Get a 3D model. Use it anywhere. Today, we're launching the Cursor + Midjourney for 3D modeling. This is Vibe Draw, the future of 3D creation:

martin

184,883 просмотров • 1 год назад

Multi-modal #LLMs understand a lot about humans. But do they understand our 3D pose? We train #PoseGPT to estimate, generate, and reason about 3D human pose (#SMPL) in images and text. This is the first true foundation model for understanding 3D humans.

Multi-modal #LLMs understand a lot about humans. But do they understand our 3D pose? We train #PoseGPT to estimate, generate, and reason about 3D human pose (#SMPL) in images and text. This is the first true foundation model for understanding 3D humans.

Michael Black

81,406 просмотров • 2 лет назад

We are introducing Hunyuan3D-Part: an open-source part-level 3D shape generation model that outperforms all existing open and close-source models. Highlights: 🔹P3-SAM: The industry's first native 3D part segmentation model. 🔹X-Part: A part generation model that achieves state-of-the-art results in controllability and shape quality. Key-features: 1️⃣Eliminates the use of 2D SAM during training, relying solely on a large-scale dataset with 3.7 million shapes and clean part annotations. 2️⃣Introduces a new automated segmentation pipeline in 3D without user intervention. 3️⃣Implements a diffusion-based part decomposition pipeline utilizing both geometry and semantic clues. Code: Weights: Tech reports: 🔸P3-SAM： → Paper: → Project page: 🔸X-Part： → Paper: → Project page: Try it now： → (Light version) Hugging Face demo: → (Full version) Hunyuan3D Studio:

We are introducing Hunyuan3D-Part: an open-source part-level 3D shape generation model that outperforms all existing open and close-source models. Highlights: 🔹P3-SAM: The industry's first native 3D part segmentation model. 🔹X-Part: A part generation model that achieves state-of-the-art results in controllability and shape quality. Key-features: 1️⃣Eliminates the use of 2D SAM during training, relying solely on a large-scale dataset with 3.7 million shapes and clean part annotations. 2️⃣Introduces a new automated segmentation pipeline in 3D without user intervention. 3️⃣Implements a diffusion-based part decomposition pipeline utilizing both geometry and semantic clues. Code: Weights: Tech reports: 🔸P3-SAM： → Paper: → Project page: 🔸X-Part： → Paper: → Project page: Try it now： → (Light version) Hugging Face demo: → (Full version) Hunyuan3D Studio:

Tencent Hy

72,522 просмотров • 9 месяцев назад

3D editing is hard: you need to ground an image + instruction and generate a faithful 3D shape in one forward pass -- no test-time optimization. So, we steer pretrained image-to-3D representations to do text-guided 3D edits; no massive 3D edit-pair dataset needed. Key trap: the “no-edit” solution is a nasty local minimum. We fix it with preference optimization, pushing the model to actually edit. Steer3D is the second work that adapts alignment ideas from LLMs to the 3D modality. SAM 3D also used DPO to improve its 3D generations.

3D editing is hard: you need to ground an image + instruction and generate a faithful 3D shape in one forward pass -- no test-time optimization. So, we steer pretrained image-to-3D representations to do text-guided 3D edits; no massive 3D edit-pair dataset needed. Key trap: the “no-edit” solution is a nasty local minimum. We fix it with preference optimization, pushing the model to actually edit. Steer3D is the second work that adapts alignment ideas from LLMs to the 3D modality. SAM 3D also used DPO to improve its 3D generations.

Georgia Gkioxari

116,061 просмотров • 7 месяцев назад

Introducing HO-Cap: A Capture System and Dataset for 3D Reconstruction and Pose Tracking of Hand-Object Interaction. We built a multi-camera system and a semi-automatic method for annotating the shape and pose of hands and objects Project page:

Introducing HO-Cap: A Capture System and Dataset for 3D Reconstruction and Pose Tracking of Hand-Object Interaction. We built a multi-camera system and a semi-automatic method for annotating the shape and pose of hands and objects Project page:

Yu Xiang

57,228 просмотров • 1 год назад

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:

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:

Tianyuan Zhang

60,842 просмотров • 2 лет назад

Introducing Texel Splatting: Perspective-Stable 3D Pixel Art open source paper+code Most 3D pixel art techniques (e.g. t3ssel8r, ProPixelizer) snap pixels to a screen grid, which only works with an orthographic camera Texel splatting solves this for perspective cameras: first,

Introducing Texel Splatting: Perspective-Stable 3D Pixel Art open source paper+code Most 3D pixel art techniques (e.g. t3ssel8r, ProPixelizer) snap pixels to a screen grid, which only works with an orthographic camera Texel splatting solves this for perspective cameras: first,

dylan

111,895 просмотров • 4 месяцев назад

🚀Create complex, modular 3D assets and scenes.🚀 Introducing #MoCA (Mixture-of-Components Attention), a new sparse attention method for compositional 3D generation. It scales to *many * components. paper: code:

🚀Create complex, modular 3D assets and scenes.🚀 Introducing #MoCA (Mixture-of-Components Attention), a new sparse attention method for compositional 3D generation. It scales to many components. paper: code:

Tengfei Wang

27,096 просмотров • 7 месяцев назад