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.

ViewCrafter can generate high-quality 3D views from single or few images using a video diffusion model! It allows for precise camera control and is useful for real-time rendering and turning text into 3D scenes. Links ⬇️

Dreaming Tulpa 🥓👑

56,461 subscribers

19,902 views • 2 years ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Wonderland: Navigating 3D Scenes from a Single Image Contributions: • First, we introduce a representation for controllable 3D generation by leveraging the generative priors from camera-guided video diffusion models. Unlike image models, video diffusion models are trained on extensive video datasets. This enables them to capture comprehensive spatial relationships within scenes across multiple views and embed a form of "3D awareness" in their latent space, which allows us to maintain 3D consistency in novel view synthesis. • Second, to achieve controllable novel view generation, we empower video models with precise control over specified camera motions. We introduce a novel dual-branch conditioning mechanism that effectively incorporates desired diverse camera trajectories into the video diffusion model. This enables expansion of a single image into a multi-view consistent capture of a 3D scene with precise pose control. • Third, to achieve efficient 3D reconstruction, we directly transform video latents into 3DGS. We propose a novel latent-based large reconstruction model (LaLRM) that lifts video latents to 3D in a feed-forward manner. With this design, during inference, our model directly predicts 3DGS from a single input image, effectively aligning the generation and reconstruction tasks—and bridging image space and 3D space—through the video latent space. Compared with reconstructing scenes from images, the video latent space offers a 256× spatial-temporal reduction while retaining essential and consistent 3D structural details. Such a high degree of compression is crucial, as it allows the LaLRM to handle a wider range of 3D scenes within the reconstruction framework, with the same memory constraints.

Wonderland: Navigating 3D Scenes from a Single Image Contributions: • First, we introduce a representation for controllable 3D generation by leveraging the generative priors from camera-guided video diffusion models. Unlike image models, video diffusion models are trained on extensive video datasets. This enables them to capture comprehensive spatial relationships within scenes across multiple views and embed a form of "3D awareness" in their latent space, which allows us to maintain 3D consistency in novel view synthesis. • Second, to achieve controllable novel view generation, we empower video models with precise control over specified camera motions. We introduce a novel dual-branch conditioning mechanism that effectively incorporates desired diverse camera trajectories into the video diffusion model. This enables expansion of a single image into a multi-view consistent capture of a 3D scene with precise pose control. • Third, to achieve efficient 3D reconstruction, we directly transform video latents into 3DGS. We propose a novel latent-based large reconstruction model (LaLRM) that lifts video latents to 3D in a feed-forward manner. With this design, during inference, our model directly predicts 3DGS from a single input image, effectively aligning the generation and reconstruction tasks—and bridging image space and 3D space—through the video latent space. Compared with reconstructing scenes from images, the video latent space offers a 256× spatial-temporal reduction while retaining essential and consistent 3D structural details. Such a high degree of compression is crucial, as it allows the LaLRM to handle a wider range of 3D scenes within the reconstruction framework, with the same memory constraints.

MrNeRF

52,849 views • 1 year ago

Create a 3D model from a single image, set of images or a text prompt in < 1 minute 😮‍💨 This new AI paper called CAT3D shows us that it’ll keep getting easier to produce 3D models from 2D images — whether it’s a sparser real world 3D scan (a few photos instead of hundreds) or your favorite 2D image generator like Midjourney (just an image). How does this magic work? “This architecture is similar to video diffusion models, but with camera pose embeddings for each image instead of time embeddings. The generated views are passed into a robust 3D reconstruction pipeline to create the 3D representation (Zip-NeRF or 3DGS)”

Create a 3D model from a single image, set of images or a text prompt in < 1 minute 😮‍💨 This new AI paper called CAT3D shows us that it’ll keep getting easier to produce 3D models from 2D images — whether it’s a sparser real world 3D scan (a few photos instead of hundreds) or your favorite 2D image generator like Midjourney (just an image). How does this magic work? “This architecture is similar to video diffusion models, but with camera pose embeddings for each image instead of time embeddings. The generated views are passed into a robust 3D reconstruction pipeline to create the 3D representation (Zip-NeRF or 3DGS)”

Bilawal Sidhu

92,919 views • 2 years ago

This is RICULOUSLY good, TRELLIS 3D Generation model by Microsoft! 🔥 Generate high-quality 3D assets from text or image prompts. Supports various formats like Radiance Fields, 3D Gaussians, and meshes Available for FREE on Hugging Face!

This is RICULOUSLY good, TRELLIS 3D Generation model by Microsoft! 🔥 Generate high-quality 3D assets from text or image prompts. Supports various formats like Radiance Fields, 3D Gaussians, and meshes Available for FREE on Hugging Face!

Vaibhav (VB) Srivastav

62,455 views • 1 year ago

MIMO aka VIGGLE on steroids can create controllable character videos from a single image! It allows users to animate characters with complex motions in real-world scenes by encoding 2D videos into 3D spatial codes for flexible control. Links ⬇️

MIMO aka VIGGLE on steroids can create controllable character videos from a single image! It allows users to animate characters with complex motions in real-world scenes by encoding 2D videos into 3D spatial codes for flexible control. Links ⬇️

Dreaming Tulpa 🥓👑

73,853 views • 2 years ago

NVIDIA introduces Edify 3D AI model You can generate high quality 3D assets from text or image input under 2 minutes! With PBR materials, quad-mesh topologies, and 4k textures. 6 wild examples:

NVIDIA introduces Edify 3D AI model You can generate high quality 3D assets from text or image input under 2 minutes! With PBR materials, quad-mesh topologies, and 4k textures. 6 wild examples:

Min Choi

399,431 views • 1 year ago

I am blown away 🤯. Check this out! CameraCtrl II: Dynamic Scene Exploration via Camera-controlled Video Diffusion Models TL;DR: "To enable broader exploration of dynamic scenes, our model can generate new video clips of the same scene based on previously generated content and user-provided camera trajectories. This approach maintains dynamic capabilities, accurate camera control, and scene consistency throughout the extended exploration." "Our model enables precise camera control across diverse scenarios while preserving dynamic scene elements, e.g." "Our method can generate videos with strong 3D consistency, which enables high-quality 3D reconstruction using the camera-controlled videos." Contributions: 1) A systematic data curation pipeline for constructing a dynamic video dataset with camera trajectory annotations; 2) A lightweight camera control injection module and corresponding training strategy that preserves dynamic video generation capabilities while adding camera control effect; 3) A clip-wise autoregressive generation recipe that enables extended range exploration of generated scenes.

I am blown away 🤯. Check this out! CameraCtrl II: Dynamic Scene Exploration via Camera-controlled Video Diffusion Models TL;DR: "To enable broader exploration of dynamic scenes, our model can generate new video clips of the same scene based on previously generated content and user-provided camera trajectories. This approach maintains dynamic capabilities, accurate camera control, and scene consistency throughout the extended exploration." "Our model enables precise camera control across diverse scenarios while preserving dynamic scene elements, e.g." "Our method can generate videos with strong 3D consistency, which enables high-quality 3D reconstruction using the camera-controlled videos." Contributions: 1) A systematic data curation pipeline for constructing a dynamic video dataset with camera trajectory annotations; 2) A lightweight camera control injection module and corresponding training strategy that preserves dynamic video generation capabilities while adding camera control effect; 3) A clip-wise autoregressive generation recipe that enables extended range exploration of generated scenes.

MrNeRF

12,633 views • 1 year ago

If you make videos, this is huge! The world’s first 3D-conditioned foundational video model has landed. Imagine literally stepping into your scene and directing the camera from inside it. Kamo-1 model from Kinetix is made for creators who want actual, precise control. Dive into the details ⬇️

If you make videos, this is huge! The world’s first 3D-conditioned foundational video model has landed. Imagine literally stepping into your scene and directing the camera from inside it. Kamo-1 model from Kinetix is made for creators who want actual, precise control. Dive into the details ⬇️

Umesh

30,733 views • 10 months ago

UI/UX Designers, you can now generate stunning 3D mockup images and videos without relying on Figma plugins. I found this amazing tool called ContentCore, It quickly generate high-quality 3D device mockups (images and video animations) to showcase your UI designs, with zero design hassle. Bookmark it for later 💜

UI/UX Designers, you can now generate stunning 3D mockup images and videos without relying on Figma plugins. I found this amazing tool called ContentCore, It quickly generate high-quality 3D device mockups (images and video animations) to showcase your UI designs, with zero design hassle. Bookmark it for later 💜

Abraham John 🦄🦓

48,047 views • 1 year ago

Introducing 📦𝗔𝗿𝘁𝗶𝗟𝗮𝘁𝗲𝗻𝘁🔧 (SIGGRAPH Asia 2025) — a high-quality 3D diffusion model that explicitly models object articulation, paving the way for richer, more realistic assets in embodied AI and simulation: – Generates fully articulated 3D objects – Physically plausible joints & motion – High-fidelity 3D Gaussian appearance – Supports generation from a single real image arXiv: Project: Code (coming soon):

Introducing 📦𝗔𝗿𝘁𝗶𝗟𝗮𝘁𝗲𝗻𝘁🔧 (SIGGRAPH Asia 2025) — a high-quality 3D diffusion model that explicitly models object articulation, paving the way for richer, more realistic assets in embodied AI and simulation: – Generates fully articulated 3D objects – Physically plausible joints & motion – High-fidelity 3D Gaussian appearance – Supports generation from a single real image arXiv: Project: Code (coming soon):

Xingang Pan

11,531 views • 10 months ago

DimensionX: Create Any 3D and 4D Scenes from a Single Image with Controllable Video Diffusion TL;DR: Create 3/4DGS from Video Diffusion Note: Some first inference code released (not all yet). Contributions (cited): • We present DimensionX, a novel framework for generating photorealistic 3D and 4D scenes from only a single image using controllable video diffusion. • We propose ST-Director, which decouples the spatial and temporal priors in video diffusion models by learning (spatial and temporal) dimension-aware modules with our curated datasets. We further enhance the hybriddimension control with a training-free composition approach according to the essence of video diffusion denoising process. • To bridge the gap between video diffusion and real-world scenes, we design a trajectory-aware mechanism for 3D generation and an identity-preserving denoising approach for 4D generation, enabling more realistic and controllable scene synthesis. • Extensive experiments manifest that our DimensionX delivers superior performance in video, 3D, and 4D generation compared with baseline methods.

DimensionX: Create Any 3D and 4D Scenes from a Single Image with Controllable Video Diffusion TL;DR: Create 3/4DGS from Video Diffusion Note: Some first inference code released (not all yet). Contributions (cited): • We present DimensionX, a novel framework for generating photorealistic 3D and 4D scenes from only a single image using controllable video diffusion. • We propose ST-Director, which decouples the spatial and temporal priors in video diffusion models by learning (spatial and temporal) dimension-aware modules with our curated datasets. We further enhance the hybriddimension control with a training-free composition approach according to the essence of video diffusion denoising process. • To bridge the gap between video diffusion and real-world scenes, we design a trajectory-aware mechanism for 3D generation and an identity-preserving denoising approach for 4D generation, enabling more realistic and controllable scene synthesis. • Extensive experiments manifest that our DimensionX delivers superior performance in video, 3D, and 4D generation compared with baseline methods.

MrNeRF

17,062 views • 1 year ago

A real-time AI motion capture model with 1B parameters. Connects to a 1080P camera or processes uploaded video to generate 3D motion data in real time. Supports Unreal Engine, Unity, and Blender, requiring 8GB of GPU VRAM for real-time processing.

A real-time AI motion capture model with 1B parameters. Connects to a 1080P camera or processes uploaded video to generate 3D motion data in real time. Supports Unreal Engine, Unity, and Blender, requiring 8GB of GPU VRAM for real-time processing.

CYANPUPPETS

37,070 views • 7 months ago

3D Gaussian Splatting for Real-Time Radiance Field Rendering paper page: Radiance Field methods have recently revolutionized novel-view synthesis of scenes captured with multiple photos or videos. However, achieving high visual quality still requires neural networks that are costly to train and render, while recent faster methods inevitably trade off speed for quality. For unbounded and complete scenes (rather than isolated objects) and 1080p resolution rendering, no current method can achieve real-time display rates. We introduce three key elements that allow us to achieve state-of-the-art visual quality while maintaining competitive training times and importantly allow high-quality real-time (>= 30 fps) novel-view synthesis at 1080p resolution. First, starting from sparse points produced during camera calibration, we represent the scene with 3D Gaussians that preserve desirable properties of continuous volumetric radiance fields for scene optimization while avoiding unnecessary computation in empty space; Second, we perform interleaved optimization/density control of the 3D Gaussians, notably optimizing anisotropic covariance to achieve an accurate representation of the scene; Third, we develop a fast visibility-aware rendering algorithm that supports anisotropic splatting and both accelerates training and allows realtime rendering. We demonstrate state-of-the-art visual quality and real-time rendering on several established datasets.

3D Gaussian Splatting for Real-Time Radiance Field Rendering paper page: Radiance Field methods have recently revolutionized novel-view synthesis of scenes captured with multiple photos or videos. However, achieving high visual quality still requires neural networks that are costly to train and render, while recent faster methods inevitably trade off speed for quality. For unbounded and complete scenes (rather than isolated objects) and 1080p resolution rendering, no current method can achieve real-time display rates. We introduce three key elements that allow us to achieve state-of-the-art visual quality while maintaining competitive training times and importantly allow high-quality real-time (>= 30 fps) novel-view synthesis at 1080p resolution. First, starting from sparse points produced during camera calibration, we represent the scene with 3D Gaussians that preserve desirable properties of continuous volumetric radiance fields for scene optimization while avoiding unnecessary computation in empty space; Second, we perform interleaved optimization/density control of the 3D Gaussians, notably optimizing anisotropic covariance to achieve an accurate representation of the scene; Third, we develop a fast visibility-aware rendering algorithm that supports anisotropic splatting and both accelerates training and allows realtime rendering. We demonstrate state-of-the-art visual quality and real-time rendering on several established datasets.

AK

634,252 views • 3 years ago

SPARK can create high-quality 3D face avatars from regular videos and track expressions and poses in real time. It improves the accuracy of 3D face reconstructions for tasks like aging, face swapping, and digital makeup. 6 examples:

SPARK can create high-quality 3D face avatars from regular videos and track expressions and poses in real time. It improves the accuracy of 3D face reconstructions for tasks like aging, face swapping, and digital makeup. 6 examples:

Dreaming Tulpa 🥓👑

193,859 views • 2 years ago

3D AI is levelling up.. Hunyuan 3D just dropped Sketch to 3D, turn any sketch into high quality 3D model and.. it can even rig & and animate your 3D character automatically something big is coming today, stay tuned. step by step tutorial:

3D AI is levelling up.. Hunyuan 3D just dropped Sketch to 3D, turn any sketch into high quality 3D model and.. it can even rig & and animate your 3D character automatically something big is coming today, stay tuned. step by step tutorial:

el.cine

235,642 views • 1 year ago

this is over.. for developers Gemini 3 can create app that turn 3D model into hologram-like 3D interactive particles and.. use hands to control it use simple text prompts, no need code literally anyone can create $100K apps now

this is over.. for developers Gemini 3 can create app that turn 3D model into hologram-like 3D interactive particles and.. use hands to control it use simple text prompts, no need code literally anyone can create $100K apps now

el.cine

499,298 views • 10 months ago

Now you can generate 3D animations directly from video. This is a behind the scenes look at 3D animator Jón Kristinsson using Move AI to capture and animate The Candy Man. Motion capture powered by AI. No suits or markers required.

Now you can generate 3D animations directly from video. This is a behind the scenes look at 3D animator Jón Kristinsson using Move AI to capture and animate The Candy Man. Motion capture powered by AI. No suits or markers required.

Move AI

458,222 views • 2 years ago

this is the future of CGI this new OpenMagic AI can add image, video or 3D product into real life video seamlessly with one click and.. it can even turn product image into 3D model automatically 10 wild examples:

this is the future of CGI this new OpenMagic AI can add image, video or 3D product into real life video seamlessly with one click and.. it can even turn product image into 3D model automatically 10 wild examples:

el.cine

121,069 views • 1 year ago