正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

Nvidia just announced Align Your Gaussians Text-to-4D with Dynamic 3D Gaussians and Composed Diffusion Models

AK

507,773 subscribers

131,322 次观看 • 2 年前 •via X (Twitter)

科学技术教育

Anya Rossi• Live Now

Private livecam show

8 条评论

AK 的头像

AK2 年前

project page:

Karsten Kreis 的头像

Karsten Kreis2 年前

Thank you! A brief thread with explanations can be found here:

Tim Wu 的头像

Tim Wu2 年前

Too bad that Nvidia never provides a demo link for their brilliant research. I'm eager to see Mona Lisa jump and roll.

Andrew S 的头像

Andrew S2 年前

Big for video game dev

Void Walker 69 的头像

Void Walker 692 年前

Too crazy.

Lukas 的头像

Lukas2 年前

the raccoon

Louiepecan.base.eth🗡🛡 的头像

Louiepecan.base.eth🗡🛡2 年前

@cerebral_valley @grandorganics

PDS_B2BMGMT 的头像

PDS_B2BMGMT2 年前

Thanks for sharing AK

相关视频

DreamPhysics: Learning Physical Properties of Dynamic 3D Gaussians from Video Diffusion Priors Code:

DreamPhysics: Learning Physical Properties of Dynamic 3D Gaussians from Video Diffusion Priors Code:

MrNeRF

12,360 次观看 • 2 年前

100M Gaussians. Streamed on a single RTX 3090. Welcome to NVIDIA AI Developer 's fVDB Reality Capture — bringing 3D Gaussian Splatting, volumetric data, and OpenUSD into one pipeline. 🎥 Full demo → #NVIDIA #GaussianSplatting #3D

100M Gaussians. Streamed on a single RTX 3090. Welcome to NVIDIA AI Developer 's fVDB Reality Capture — bringing 3D Gaussian Splatting, volumetric data, and OpenUSD into one pipeline. 🎥 Full demo → #NVIDIA #GaussianSplatting #3D

Jonathan Stephens

36,725 次观看 • 8 个月前

Current 3D generative models are slow and low quality. We present GRM, a large-scale model that reconstructs 3D Gaussians in 0.1s and generates high-quality 3D assets from text or single images in a few seconds. Demo: 1/4

Current 3D generative models are slow and low quality. We present GRM, a large-scale model that reconstructs 3D Gaussians in 0.1s and generates high-quality 3D assets from text or single images in a few seconds. Demo: 1/4

Gordon Wetzstein

19,210 次观看 • 2 年前

NVIDIA just showed some new relighting capabilities using gaussians, though this is pure ray tracing (no splatting). TRON extends their ray tracing library (3DGRT) to get an editable 3D material scaffold.

NVIDIA just showed some new relighting capabilities using gaussians, though this is pure ray tracing (no splatting). TRON extends their ray tracing library (3DGRT) to get an editable 3D material scaffold.

Radiance Fields

28,421 次观看 • 15 天前

Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Models turn the publicly available, state-of-the-art text-to-image LDM Stable Diffusion into an efficient and expressive text-to-video model with resolution up to 1280 x 2048 abs: project page:

Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Models turn the publicly available, state-of-the-art text-to-image LDM Stable Diffusion into an efficient and expressive text-to-video model with resolution up to 1280 x 2048 abs: project page:

AK

718,760 次观看 • 3 年前

[SIGGRAPH '25] TeGA: Texture Space Gaussian Avatars for High-Resolution Dynamic Head Modeling Note: On the left that's a 3DGS rendering! Contributions: 1. We propose a simple approach for rigging 3D Gaussians within the continuous tangent space of 3DMM face models, allowing Gaussians to move freely across mesh triangles. 2. We propose a novel CNN-based deformation model that is agnostic to the number of 3D Gaussians, naturally enabling adaptively densification of the representation to improve detail where most needed, with expression-dependent shading. 3. We show significant improvements over baseline SOTA methods and demonstrate the ability to render even extreme close-up images at high quality.

[SIGGRAPH '25] TeGA: Texture Space Gaussian Avatars for High-Resolution Dynamic Head Modeling Note: On the left that's a 3DGS rendering! Contributions: 1. We propose a simple approach for rigging 3D Gaussians within the continuous tangent space of 3DMM face models, allowing Gaussians to move freely across mesh triangles. 2. We propose a novel CNN-based deformation model that is agnostic to the number of 3D Gaussians, naturally enabling adaptively densification of the representation to improve detail where most needed, with expression-dependent shading. 3. We show significant improvements over baseline SOTA methods and demonstrate the ability to render even extreme close-up images at high quality.

MrNeRF

29,010 次观看 • 1 年前

Extract accurate depth from your 3D gaussians! Fast, accurate, and easy to use. Code of RaDe-GS is released! project page: code: paper: No need to change your 3D GS representations, we propose a play-and-plug rasterizer to extract accurate depth and normal from 3D gaussians, leading to the possibility of high-quality geometry reconstruction. It's quite efficient and fast, achieving 0.69mm errors on DTU dataset in only 5 minutes. Very easy to adopt the rasterizer in your any 3dgs projects.

Extract accurate depth from your 3D gaussians! Fast, accurate, and easy to use. Code of RaDe-GS is released! project page: code: paper: No need to change your 3D GS representations, we propose a play-and-plug rasterizer to extract accurate depth and normal from 3D gaussians, leading to the possibility of high-quality geometry reconstruction. It's quite efficient and fast, achieving 0.69mm errors on DTU dataset in only 5 minutes. Very easy to adopt the rasterizer in your any 3dgs projects.

Xiao-Xiao Long

31,290 次观看 • 2 年前

Nvidia presents Align Your Steps Optimizing Sampling Schedules in Diffusion Models Diffusion models (DMs) have established themselves as the state-of-the-art generative modeling approach in the visual domain and beyond. A crucial drawback of DMs is their slow sampling speed,

Nvidia presents Align Your Steps Optimizing Sampling Schedules in Diffusion Models Diffusion models (DMs) have established themselves as the state-of-the-art generative modeling approach in the visual domain and beyond. A crucial drawback of DMs is their slow sampling speed,

AK

32,888 次观看 • 2 年前

Every photo on your phone is now a portal. Lyra 2.0 by NVIDIA - explorable 3D world gen from single images! -long-horizon camera trajectories with 3D consistency; - DMD-distilled 4-step inference; - outputs 3D Gaussians + meshes via Wan 2.1-14B; - minimal drift. Game devs are cooking entire levels from one piece of concept art

Every photo on your phone is now a portal. Lyra 2.0 by NVIDIA - explorable 3D world gen from single images! -long-horizon camera trajectories with 3D consistency; - DMD-distilled 4-step inference; - outputs 3D Gaussians + meshes via Wan 2.1-14B; - minimal drift. Game devs are cooking entire levels from one piece of concept art

Wildminder

20,854 次观看 • 3 个月前

Harness the latest generative AI models locally on your RTX AI PC with NVIDIA NIM Microservices and AI Blueprints. 🎨🖼️ Learn how NVIDIA NIM, @BFL_ML Flux, and ComfyUI empower creators to use 3D objects and simple text prompts to bring ideas to life.

Harness the latest generative AI models locally on your RTX AI PC with NVIDIA NIM Microservices and AI Blueprints. 🎨🖼️ Learn how NVIDIA NIM, @BFL_ML Flux, and ComfyUI empower creators to use 3D objects and simple text prompts to bring ideas to life.

NVIDIA RTX Spark

305,987 次观看 • 1 年前

⚡️ Introducing Bolt3D ⚡️ Bolt3D generates interactive 3D scenes in less than 7 seconds on a single GPU from one or more images. It features a latent diffusion model that *directly* generates 3D Gaussians of seen and unseen regions, without any test time optimization. 🧵👇 (1/9)

⚡️ Introducing Bolt3D ⚡️ Bolt3D generates interactive 3D scenes in less than 7 seconds on a single GPU from one or more images. It features a latent diffusion model that directly generates 3D Gaussians of seen and unseen regions, without any test time optimization. 🧵👇 (1/9)

Stan Szymanowicz

125,888 次观看 • 1 年前

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

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 次观看 • 3 年前

Nvidia presents Edify 3D! The method can generate high-quality 3D assets from text descriptions. It uses a diffusion model to create detailed quad-mesh topologies and high-resolution textures in under 2 minutes.

Nvidia presents Edify 3D! The method can generate high-quality 3D assets from text descriptions. It uses a diffusion model to create detailed quad-mesh topologies and high-resolution textures in under 2 minutes.

Dreaming Tulpa 🥓👑

39,517 次观看 • 1 年前

V3D Video Diffusion Models are Effective 3D Generators Automatic 3D generation has recently attracted widespread attention. Recent methods have greatly accelerated the generation speed, but usually produce less-detailed objects due to limited model capacity or 3D data. Motivated by recent advancements in video diffusion models, we introduce V3D, which leverages the world simulation capacity of pre-trained video diffusion models to facilitate 3D generation. To fully unleash the potential of video diffusion to perceive the 3D world, we further introduce geometrical consistency prior and extend the video diffusion model to a multi-view consistent 3D generator. Benefiting from this, the state-of-the-art video diffusion model could be fine-tuned to generate 360degree orbit frames surrounding an object given a single image. With our tailored reconstruction pipelines, we can generate high-quality meshes or 3D Gaussians within 3 minutes. Furthermore, our method can be extended to scene-level novel view synthesis, achieving precise control over the camera path with sparse input views. Extensive experiments demonstrate the superior performance of the proposed approach, especially in terms of generation quality and multi-view consistency

V3D Video Diffusion Models are Effective 3D Generators Automatic 3D generation has recently attracted widespread attention. Recent methods have greatly accelerated the generation speed, but usually produce less-detailed objects due to limited model capacity or 3D data. Motivated by recent advancements in video diffusion models, we introduce V3D, which leverages the world simulation capacity of pre-trained video diffusion models to facilitate 3D generation. To fully unleash the potential of video diffusion to perceive the 3D world, we further introduce geometrical consistency prior and extend the video diffusion model to a multi-view consistent 3D generator. Benefiting from this, the state-of-the-art video diffusion model could be fine-tuned to generate 360degree orbit frames surrounding an object given a single image. With our tailored reconstruction pipelines, we can generate high-quality meshes or 3D Gaussians within 3 minutes. Furthermore, our method can be extended to scene-level novel view synthesis, achieving precise control over the camera path with sparse input views. Extensive experiments demonstrate the superior performance of the proposed approach, especially in terms of generation quality and multi-view consistency

AK

31,997 次观看 • 2 年前

📢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!

📢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

39,496 次观看 • 1 年前

📢 Check out 𝗥𝗲𝗹𝗶𝗴𝗵𝘁𝗮𝗯𝗹𝗲 𝗚𝗮𝘂𝘀𝘀𝗶𝗮𝗻 𝗖𝗼𝗱𝗲𝗰 𝗔𝘃𝗮𝘁𝗮𝗿𝘀! Our latest codec avatars using 3D Gaussians generalize to novel lighting (OLAT, envmap) with *all-frequency* reflection (see video for hair and eye reflection) in real-time!

📢 Check out 𝗥𝗲𝗹𝗶𝗴𝗵𝘁𝗮𝗯𝗹𝗲 𝗚𝗮𝘂𝘀𝘀𝗶𝗮𝗻 𝗖𝗼𝗱𝗲𝗰 𝗔𝘃𝗮𝘁𝗮𝗿𝘀! Our latest codec avatars using 3D Gaussians generalize to novel lighting (OLAT, envmap) with all-frequency reflection (see video for hair and eye reflection) in real-time!

Shunsuke Saito

45,945 次观看 • 2 年前

Zhou et al., "PAGE-4D: Disentangled Pose and Geometry Estimation for 4D Perception" VGGT extended to dynamic scenes with a dynamic mask predictor.

Zhou et al., "PAGE-4D: Disentangled Pose and Geometry Estimation for 4D Perception" VGGT extended to dynamic scenes with a dynamic mask predictor.

Kwang Moo Yi

11,546 次观看 • 8 个月前

3D AI is leveling up! Rodin 3D AI can create stunning, high-quality 3D models from just text or image inputs. And with its latest update, it can even generate 8K HDRI textures to bring your models to life. Check out the link in the comments!

3D AI is leveling up! Rodin 3D AI can create stunning, high-quality 3D models from just text or image inputs. And with its latest update, it can even generate 8K HDRI textures to bring your models to life. Check out the link in the comments!

el.cine

46,032 次观看 • 1 年前

VSTAR Generative Temporal Nursing for Longer Dynamic Video Synthesis Despite tremendous progress in the field of text-to-video (T2V) synthesis, open-sourced T2V diffusion models struggle to generate longer videos with dynamically varying and evolving content. They tend to

VSTAR Generative Temporal Nursing for Longer Dynamic Video Synthesis Despite tremendous progress in the field of text-to-video (T2V) synthesis, open-sourced T2V diffusion models struggle to generate longer videos with dynamically varying and evolving content. They tend to

AK

36,982 次观看 • 2 年前