Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

🚀 Introducing #DreamCraft3D, our breakthrough hierarchical technique for 3D content generation. Leading the way in AIGC, we're redefining 3D generation: Project page: Paper: Code:

deepseek_ai's profile picture

DeepSeek

1,041,017 subscribers

16,400 Aufrufe • vor 2 Jahren •via X (Twitter)

Wissenschaft & TechnologieNachrichten & PolitikBildung#DreamCraft3D
LIVE

Anya Rossi• Live Now

Private livecam show

10 Kommentare

Profilbild von muhammed rekani
muhammed rekanivor 1 Jahr

Who is here after the R1 storm 😂

Profilbild von Adams Pro 𝕏 👨‍💻👓
Adams Pro 𝕏 👨‍💻👓vor 1 Jahr

Have to check your first tweet

Profilbild von DeepSeek Community ®
DeepSeek Community ®vor 1 Jahr

This was the first post (tweet) I found from the DeepSeek profile, and no one could have imagined at the time that this company would take off like a rocket 🚀 and surpass the world's leading AI models. Great job, team! 👏

Profilbild von matt
mattvor 1 Jahr

@FlippingProfits they really fw u huh

Profilbild von RIckk
RIckkvor 1 Jahr

DreamCraft3D FTWpVA3wPBBCD8Vdr8Vshfhow7BvVE7sPmqFKu7Wpump

Profilbild von Sophisticated_Brat
Sophisticated_Bratvor 1 Jahr

Damnnnn

Profilbild von ram4nd
ram4ndvor 1 Jahr

This is crazy

Profilbild von Catherine Li
Catherine Livor 1 Jahr

光速 VS. 宇宙膨胀的速度<1

Profilbild von Mozzie.
Mozzie.vor 1 Jahr

Feel like being the whales stomach

Profilbild von ShadowFates 🐦
ShadowFates 🐦vor 1 Jahr

where we go, where this legendary A.I gets Started

Ähnliche Videos

🚀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:
0:31

🚀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 Aufrufe • vor 6 Monaten

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.
2:32

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 Aufrufe • vor 2 Jahren

SceneDreamer: Unbounded 3D Scene Generation from 2D Image Collections abs: project page:
0:58

SceneDreamer: Unbounded 3D Scene Generation from 2D Image Collections abs: project page:

AK

317,619 Aufrufe • vor 3 Jahren

We are thrilled to announce a major upgrade to our open-source 3D generation model, introducing two groundbreaking new versions: 3D 2.0 MV (Multi-View Generation) and 3D 2.0 Mini! 3D 2.0 MV : 3D 2.0Mini:
0:39

We are thrilled to announce a major upgrade to our open-source 3D generation model, introducing two groundbreaking new versions: 3D 2.0 MV (Multi-View Generation) and 3D 2.0 Mini! 3D 2.0 MV : 3D 2.0Mini:

Tencent HY

134,410 Aufrufe • vor 1 Jahr

Introducing ShapeR, a method for robust conditional 3D shape generation from casually captured sequences. ShapeR leverages a rectified flow transformer conditioned on per-object multimodal data to turn casual image sequences into full metric scene reconstructions. Project Page: Paper: Links to code and huggingface below ⬇️
0:58

Introducing ShapeR, a method for robust conditional 3D shape generation from casually captured sequences. ShapeR leverages a rectified flow transformer conditioned on per-object multimodal data to turn casual image sequences into full metric scene reconstructions. Project Page: Paper: Links to code and huggingface below ⬇️

Yawar Siddiqui

70,391 Aufrufe • vor 5 Monaten

Introducing 𝐒𝐀𝐑𝟑𝐃, which tokenizes 3D objects into multiscale tokens and generates 3D objects by autoregressive next-scale prediction. 𝐒𝐀𝐑𝟑𝐃 enables fast 3D generation and comprehensive 3D understanding. arXiv: Project:
0:20

Introducing 𝐒𝐀𝐑𝟑𝐃, which tokenizes 3D objects into multiscale tokens and generates 3D objects by autoregressive next-scale prediction. 𝐒𝐀𝐑𝟑𝐃 enables fast 3D generation and comprehensive 3D understanding. arXiv: Project:

Xingang Pan

28,248 Aufrufe • vor 1 Jahr

🚀High-Res 3D Text-to-Texture🚀 🎨#MVPaint delivers high-res 3D textures with minimal UV wrapping dependency and high versatility using synchronized multi-view diffusion 📑 Paper: 🏠 Project Page: 🧑‍💻 Code:
0:39

🚀High-Res 3D Text-to-Texture🚀 🎨#MVPaint delivers high-res 3D textures with minimal UV wrapping dependency and high versatility using synchronized multi-view diffusion 📑 Paper: 🏠 Project Page: 🧑‍💻 Code:

Ziwei Liu

28,122 Aufrufe • vor 1 Jahr

🚀Turn Single Image into 3D Human🚀 #GeneMAN is a generalizable single-image 3D human reconstruction framework that turns in-the-wild images into high-quality 3D humans with ease 🔗Project: 📜Paper: 🧑‍💻Code:
1:04

🚀Turn Single Image into 3D Human🚀 #GeneMAN is a generalizable single-image 3D human reconstruction framework that turns in-the-wild images into high-quality 3D humans with ease 🔗Project: 📜Paper: 🧑‍💻Code:

Ziwei Liu

26,953 Aufrufe • vor 1 Jahr

DreamBooth3D: Subject-Driven Text-to-3D Generation Personalized 3D models from just a few casual photos, with text-driven modifications abs: project page:
1:49

DreamBooth3D: Subject-Driven Text-to-3D Generation Personalized 3D models from just a few casual photos, with text-driven modifications abs: project page:

AK

107,503 Aufrufe • vor 3 Jahren

Vibe Code Application 3d Generation and Photo
0:20

Vibe Code Application 3d Generation and Photo

Slava

52,114 Aufrufe • vor 1 Monat

🚀After two nominations at 2024, we’re thrilled to share that we finally won the ACM SIGGRAPH 2025 Best Paper Award🏆🏆🏆! SIGGRAPH has always been our guiding star. In early 2023, our team at DEEMOS embarked on universal 3D generation, exploring Diffusion Transformer and AutoRegressive paths. These evolved into CLAY and DressCode, both nominated for SIGGRAPH Best Paper. Built on prior work, they pushed the boundaries of innovation, contributing unique value to the community. Since launching - Rodin in June 2024, we’ve become a leading 3D generation platform. Additionally, we have an unannounced project, BANG, which serves as the foundation for Rodin Gen-2. This is our proudest innovative breakthrough of 2024. Stay tuned for its unveiling soon!
0:25

🚀After two nominations at 2024, we’re thrilled to share that we finally won the ACM SIGGRAPH 2025 Best Paper Award🏆🏆🏆! SIGGRAPH has always been our guiding star. In early 2023, our team at DEEMOS embarked on universal 3D generation, exploring Diffusion Transformer and AutoRegressive paths. These evolved into CLAY and DressCode, both nominated for SIGGRAPH Best Paper. Built on prior work, they pushed the boundaries of innovation, contributing unique value to the community. Since launching - Rodin in June 2024, we’ve become a leading 3D generation platform. Additionally, we have an unannounced project, BANG, which serves as the foundation for Rodin Gen-2. This is our proudest innovative breakthrough of 2024. Stay tuned for its unveiling soon!

Deemos

12,998 Aufrufe • vor 1 Jahr

Introducing AI 3D Generation ✨ 🔥 Text to 3D 🖼️ Image to 3D 🌳 Remix 📐 Editor integration & Exports Available now!
0:32

Introducing AI 3D Generation ✨ 🔥 Text to 3D 🖼️ Image to 3D 🌳 Remix 📐 Editor integration & Exports Available now!

Spline

705,628 Aufrufe • vor 2 Jahren

🚨 Hunyuan 3D 3.1 Pro and Rapid is here on fal! 🎯 Pro: High-fidelity Image-to-3D and Text-to-3D generation ⚡ Rapid: Speed-optimized 3D generation ✨ Smart Topology and Part generation for advanced 3D workflows
0:21

🚨 Hunyuan 3D 3.1 Pro and Rapid is here on fal! 🎯 Pro: High-fidelity Image-to-3D and Text-to-3D generation ⚡ Rapid: Speed-optimized 3D generation ✨ Smart Topology and Part generation for advanced 3D workflows

fal

26,048 Aufrufe • vor 4 Monaten

Yay, finally! Introducing Vision Banana🍌 from Google DeepMind, our unified model that outperforms SoTA specialist models on various vision tasks! By treating 2D/3D vision tasks as image generation, we unlock a new foundation for CV. Project page: (1/5)
0:25

Yay, finally! Introducing Vision Banana🍌 from Google DeepMind, our unified model that outperforms SoTA specialist models on various vision tasks! By treating 2D/3D vision tasks as image generation, we unlock a new foundation for CV. Project page: (1/5)

Songyou Peng

283,432 Aufrufe • vor 1 Monat

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:
1:54

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

17,858 Aufrufe • vor 6 Monaten

🚨 Paper Alert Our recent breakthrough CAST: Component-Aligned 3D Scene Reconstruction from an RGB Image has been accepted by ACM SIGGRAPH 2025 Journal Track! CAST will change the way create scenes in 3D Art and Embody AI. 🚀Soon available at 👇Details
3:41

🚨 Paper Alert Our recent breakthrough CAST: Component-Aligned 3D Scene Reconstruction from an RGB Image has been accepted by ACM SIGGRAPH 2025 Journal Track! CAST will change the way create scenes in 3D Art and Embody AI. 🚀Soon available at 👇Details

Deemos

34,110 Aufrufe • vor 1 Jahr

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:
0:39

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 Aufrufe • vor 8 Monaten

I'm excited to share our new work, VistaDream, which generates a 3D Gaussian field from a single-view image. The codes have already been released. Project page: (with interactive demos) Code: Paper:
0:27

I'm excited to share our new work, VistaDream, which generates a 3D Gaussian field from a single-view image. The codes have already been released. Project page: (with interactive demos) Code: Paper:

Yuan Liu

79,592 Aufrufe • vor 1 Jahr

3D Gen has entered the era of Post Training🚀 Our paper for Rodin Gen-2, 💥BANG: Dividing #3D Assets via Generative Exploded Dynamics will be presented ACM SIGGRAPH Inspired by the Understanding by Generation trends on LLM, BANG turns part division into generative task. 👇(1/6)
4:18

3D Gen has entered the era of Post Training🚀 Our paper for Rodin Gen-2, 💥BANG: Dividing #3D Assets via Generative Exploded Dynamics will be presented ACM SIGGRAPH Inspired by the Understanding by Generation trends on LLM, BANG turns part division into generative task. 👇(1/6)

Hyper3D by Deemos

112,461 Aufrufe • vor 10 Monaten

We’re also publishing two research papers on the approaches we used for high quality 3D model generation & texture generation based on text prompts that are behind the Meta 3D Gen system. Meta 3D AssetGen ➡️ Meta 3D TextureGen ➡️
0:37

We’re also publishing two research papers on the approaches we used for high quality 3D model generation & texture generation based on text prompts that are behind the Meta 3D Gen system. Meta 3D AssetGen ➡️ Meta 3D TextureGen ➡️

AI at Meta

72,914 Aufrufe • vor 1 Jahr