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.

Track4World. Feedforward world-centric dense 3D tracking; - tracks every pixel in 3D. - 16-frame sequences in 3.4s with 14GB VRAM; - Depth Anything v3 as backbone.

Wildminder

10,368 subscribers

18,990 views • 5 months 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

Excited to share Track4World, feedforward 3D tracking of all pixels in the world-centric coordinate system. Code has been released, and welcome to try it! Homepage: Code: Paper:

Excited to share Track4World, feedforward 3D tracking of all pixels in the world-centric coordinate system. Code has been released, and welcome to try it! Homepage: Code: Paper:

Yuan Liu

20,054 views • 5 months ago

Introducing VGGT (CVPR'25), a feedforward Transformer that directly infers all key 3D attributes from one, a few, or hundreds of images, in seconds! No expensive optimization needed, yet delivers SOTA results for: ✅ Camera Pose Estimation ✅ Multi-view Depth Estimation ✅ Dense Point Cloud Reconstruction ✅ Point Tracking Project Page: Code & Weights:

Introducing VGGT (CVPR'25), a feedforward Transformer that directly infers all key 3D attributes from one, a few, or hundreds of images, in seconds! No expensive optimization needed, yet delivers SOTA results for: ✅ Camera Pose Estimation ✅ Multi-view Depth Estimation ✅ Dense Point Cloud Reconstruction ✅ Point Tracking Project Page: Code & Weights:

Jianyuan

203,270 views • 1 year ago

update: enhanced 3d world generation just dropped in Teleport with World Labs marble 1.1 16 iPhone photos → fully explorable 3d world in minutes 📸 golden gai, shinjuku 🇯🇵

update: enhanced 3d world generation just dropped in Teleport with World Labs marble 1.1 16 iPhone photos → fully explorable 3d world in minutes 📸 golden gai, shinjuku 🇯🇵

Martin Maly

116,147 views • 3 months ago

Took it further with Omma AI, (Spline ) now it works on video, and everything working in a Web Browser. Drop a video, Depth Anything v2 calculates the depth map frame by frame, and Three.js renders a fully lit 3D mesh in real time. Depth estimation on video in the browser +Automatic baking pass + Dynamic lighting reacting to the geometry #vibecoding #threejs #webgl

Took it further with Omma AI, (Spline ) now it works on video, and everything working in a Web Browser. Drop a video, Depth Anything v2 calculates the depth map frame by frame, and Three.js renders a fully lit 3D mesh in real time. Depth estimation on video in the browser +Automatic baking pass + Dynamic lighting reacting to the geometry #vibecoding #threejs #webgl

Joseph Azar

148,148 views • 3 months ago

3D extrusion shader in Figma. Draw content inside a frame with the shader applied and it'll be transformed into 3D live as you're drawing. Stack with other shaders and animate to create 3D animations. Clone this file to grab the shader!

3D extrusion shader in Figma. Draw content inside a frame with the shader applied and it'll be transformed into 3D live as you're drawing. Stack with other shaders and animate to create 3D animations. Clone this file to grab the shader!

Piers Cowburn

46,812 views • 1 month ago

Today, we are open-sourcing Hunyuan World 1.1 (WorldMirror), a universal feed-forward 3D reconstruction model. 🚀🚀🚀 While our previously released Hunyuan World 1.0 (open-sourced, lite version deployable on consumer GPUs) focused on generating 3D worlds from text or single-view images, Hunyuan World 1.1 significantly expands the input scope by unlocking video-to-3D and multi-view-to-3D world creation. Highlights: 🔹Any Input, Maximized Flexibility and Fidelity: Flexibly integrates diverse geometric priors (camera poses, intrinsics, depth maps) to resolve structural ambiguities and ensure geometrically consistent 3D outputs. 🔹Any Output, SOTA Results：This elegant architecture simultaneously generates multiple 3D representations: dense point clouds, multi-view depth maps, camera parameters, surface normals, and 3D Gaussian Splattings. 🔹Single-GPU & Fast Inference: As an all-in-one, feed-forward model, Hunyuan World 1.1 runs on a single GPU and delivers all 3D attributes in a single forward pass, within seconds. 🌐Project Page: 🔗Github： 🤗Hugging Face： ✨Demo: 📄Technical Report:

Today, we are open-sourcing Hunyuan World 1.1 (WorldMirror), a universal feed-forward 3D reconstruction model. 🚀🚀🚀 While our previously released Hunyuan World 1.0 (open-sourced, lite version deployable on consumer GPUs) focused on generating 3D worlds from text or single-view images, Hunyuan World 1.1 significantly expands the input scope by unlocking video-to-3D and multi-view-to-3D world creation. Highlights: 🔹Any Input, Maximized Flexibility and Fidelity: Flexibly integrates diverse geometric priors (camera poses, intrinsics, depth maps) to resolve structural ambiguities and ensure geometrically consistent 3D outputs. 🔹Any Output, SOTA Results：This elegant architecture simultaneously generates multiple 3D representations: dense point clouds, multi-view depth maps, camera parameters, surface normals, and 3D Gaussian Splattings. 🔹Single-GPU & Fast Inference: As an all-in-one, feed-forward model, Hunyuan World 1.1 runs on a single GPU and delivers all 3D attributes in a single forward pass, within seconds. 🌐Project Page: 🔗Github： 🤗Hugging Face： ✨Demo: 📄Technical Report:

Tencent Hy

168,530 views • 9 months ago

I prompted Omma to build a #threejs app with real dynamic lighting on a 3D mesh - generated from a single image, using Depth Anything v2 + Transformers from Hugging Face ⚡ Depth estimation in the browser 🫧 3D mesh from the depth map 💡 Dynamic lighting reacting to the geometry No manual code. Pure AI prompting. The future of 3D on the web feels wide open.

I prompted Omma to build a #threejs app with real dynamic lighting on a 3D mesh - generated from a single image, using Depth Anything v2 + Transformers from Hugging Face ⚡ Depth estimation in the browser 🫧 3D mesh from the depth map 💡 Dynamic lighting reacting to the geometry No manual code. Pure AI prompting. The future of 3D on the web feels wide open.

Joseph Azar

14,041 views • 3 months ago

We live in a world where you can dynamically generate an SVG with 100 sample points and 3D logic inside a single browser frame. crazy

We live in a world where you can dynamically generate an SVG with 100 sample points and 3D logic inside a single browser frame. crazy

David Aerne

53,793 views • 6 months ago

When we were kids, we imagined we could play a part in the hero's world and that they could help us in ours. We're trying to capture that feeling with these 2D and 3D sequences!

When we were kids, we imagined we could play a part in the hero's world and that they could help us in ours. We're trying to capture that feeling with these 2D and 3D sequences!

The Plucky Squire 📖

264,858 views • 2 years ago

here's a pixel perfect 3d renderer written with no libraries in c and opengl (ok, and imgui). been a while since i posted anything i programmed on here. i wrote this back in january and showed Zizhen Andrew but never did anything with it. 1/3

here's a pixel perfect 3d renderer written with no libraries in c and opengl (ok, and imgui). been a while since i posted anything i programmed on here. i wrote this back in january and showed Zizhen Andrew but never did anything with it. 1/3

benji

85,918 views • 2 years ago

ViPE: Video Pose Engine for 3D Geometric Perception Contributions: • A robust and efficient framework, ViPE, for estimating camera parameters and dense depth from diverse, in-the-wild videos. • A system design that integrates the strengths of classical SLAM (efficiency, scalability) and learned models (robustness), with key improvements in efficiency, dynamic object handling, and depth quality over prior work. • A large-scale dataset of annotated videos, created using ViPE, to facilitate future research in 3D computer vision.

ViPE: Video Pose Engine for 3D Geometric Perception Contributions: • A robust and efficient framework, ViPE, for estimating camera parameters and dense depth from diverse, in-the-wild videos. • A system design that integrates the strengths of classical SLAM (efficiency, scalability) and learned models (robustness), with key improvements in efficiency, dynamic object handling, and depth quality over prior work. • A large-scale dataset of annotated videos, created using ViPE, to facilitate future research in 3D computer vision.

MrNeRF

42,553 views • 11 months ago

3D Bears are here🚀 They represent the first glance into the future of the upcoming Bear World Metaverse. Every Bear NFT holder will get the 3D Bear for free which will serve as an avatar in the Bear World. We're also planning unique 3D accessories and clothes for our Bears👘

Sui Bears | SOLD OUT

29,712 views • 3 years ago

DeepAgent Now Combines Deep Research With Interactive Dashboard, Including 3D Charts. As of today, DeepAgent can - do very deep research on any particular topic - create interactive charts, including 3D plots - lay it all out on a rich dashboard with filters, etc It is almost 100% correct and can do it with a single prompt! Do in-depth research, get great data insights, and analyze anything in minutes

DeepAgent Now Combines Deep Research With Interactive Dashboard, Including 3D Charts. As of today, DeepAgent can - do very deep research on any particular topic - create interactive charts, including 3D plots - lay it all out on a rich dashboard with filters, etc It is almost 100% correct and can do it with a single prompt! Do in-depth research, get great data insights, and analyze anything in minutes

Bindu Reddy

12,232 views • 1 year ago

Classic pixel art evolves in FINAL FANTASY RESONANCE, the first FINAL FANTASY in HD-2D. With dynamic camera angles, pixelized 3D models, and a visually striking world, embark on a adventure to uncover the truth behind a force that threatens your world.

Classic pixel art evolves in FINAL FANTASY RESONANCE, the first FINAL FANTASY in HD-2D. With dynamic camera angles, pixelized 3D models, and a visually striking world, embark on a adventure to uncover the truth behind a force that threatens your world.

Square Enix

517,506 views • 1 month ago

3D-LLM: Injecting the 3D World into Large Language Models paper page: Large language models (LLMs) and Vision-Language Models (VLMs) have been proven to excel at multiple tasks, such as commonsense reasoning. Powerful as these models can be, they are not grounded in the 3D physical world, which involves richer concepts such as spatial relationships, affordances, physics, layout, and so on. In this work, we propose to inject the 3D world into large language models and introduce a whole new family of 3D-LLMs. Specifically, 3D-LLMs can take 3D point clouds and their features as input and perform a diverse set of 3D-related tasks, including captioning, dense captioning, 3D question answering, task decomposition, 3D grounding, 3D-assisted dialog, navigation, and so on. Using three types of prompting mechanisms that we design, we are able to collect over 300k 3D-language data covering these tasks. To efficiently train 3D-LLMs, we first utilize a 3D feature extractor that obtains 3D features from rendered multi- view images. Then, we use 2D VLMs as our backbones to train our 3D-LLMs. By introducing a 3D localization mechanism, 3D-LLMs can better capture 3D spatial information. Experiments on ScanQA show that our model outperforms state-of-the-art baselines by a large margin (e.g., the BLEU-1 score surpasses state-of-the-art score by 9%). Furthermore, experiments on our held-in datasets for 3D captioning, task composition, and 3D-assisted dialogue show that our model outperforms 2D VLMs. Qualitative examples also show that our model could perform more tasks beyond the scope of existing LLMs and VLMs.

3D-LLM: Injecting the 3D World into Large Language Models paper page: Large language models (LLMs) and Vision-Language Models (VLMs) have been proven to excel at multiple tasks, such as commonsense reasoning. Powerful as these models can be, they are not grounded in the 3D physical world, which involves richer concepts such as spatial relationships, affordances, physics, layout, and so on. In this work, we propose to inject the 3D world into large language models and introduce a whole new family of 3D-LLMs. Specifically, 3D-LLMs can take 3D point clouds and their features as input and perform a diverse set of 3D-related tasks, including captioning, dense captioning, 3D question answering, task decomposition, 3D grounding, 3D-assisted dialog, navigation, and so on. Using three types of prompting mechanisms that we design, we are able to collect over 300k 3D-language data covering these tasks. To efficiently train 3D-LLMs, we first utilize a 3D feature extractor that obtains 3D features from rendered multi- view images. Then, we use 2D VLMs as our backbones to train our 3D-LLMs. By introducing a 3D localization mechanism, 3D-LLMs can better capture 3D spatial information. Experiments on ScanQA show that our model outperforms state-of-the-art baselines by a large margin (e.g., the BLEU-1 score surpasses state-of-the-art score by 9%). Furthermore, experiments on our held-in datasets for 3D captioning, task composition, and 3D-assisted dialogue show that our model outperforms 2D VLMs. Qualitative examples also show that our model could perform more tasks beyond the scope of existing LLMs and VLMs.

AK

249,708 views • 3 years ago

HunyuanWorld-Voyager is here and fully open-source! The world’s first ultra-long-range world model with native 3D reconstruction, redefining AI-driven spatial intelligence for VR, gaming, and simulations. ✅Direct 3D Output: Exports point cloud videos to 3D formats without tools like COLMAP, enabling instant 3D application use. ✅Innovative 3D Memory: Introduces a scalable world caching mechanism, ensuring geometric consistency across any camera trajectory. ✅Top-Ranked Performance: #1 on Stanford’s WorldScore, excelling in video generation and 3D reconstruction benchmarks.( Built on HunyuanWorld 1.0, Voyager blends video generation with 3D modeling, delivering camera-controlled, high-fidelity RGB-D sequences. Control scenes via keyboard or joystick for unmatched 3D consistency. Explore now: 🌐Project Page: 🔗GitHub: 🤗HuggingFace: 📝Technical Details:

HunyuanWorld-Voyager is here and fully open-source! The world’s first ultra-long-range world model with native 3D reconstruction, redefining AI-driven spatial intelligence for VR, gaming, and simulations. ✅Direct 3D Output: Exports point cloud videos to 3D formats without tools like COLMAP, enabling instant 3D application use. ✅Innovative 3D Memory: Introduces a scalable world caching mechanism, ensuring geometric consistency across any camera trajectory. ✅Top-Ranked Performance: #1 on Stanford’s WorldScore, excelling in video generation and 3D reconstruction benchmarks.( Built on HunyuanWorld 1.0, Voyager blends video generation with 3D modeling, delivering camera-controlled, high-fidelity RGB-D sequences. Control scenes via keyboard or joystick for unmatched 3D consistency. Explore now: 🌐Project Page: 🔗GitHub: 🤗HuggingFace: 📝Technical Details:

Tencent Hy

198,289 views • 11 months ago

📢Face Anything: 4D Face Reconstruction from Any Image Sequence Transformer model for 4D face reconstruction and dense tracking: - predict canonical facial coordinates per pixel - tracking as reconstruction in canonical space - geometry + correspondences in one forward pass Key idea: a shared canonical space across frames - correspondences as nearest neighbors - no motion or deformation estimation Stable geometry and tracking, even under large expressions and viewpoint changes - check out our results! 🌐 ▶️ Great work by Umut Kocasarı, Simon Giebenhain, Richard Shaw

📢Face Anything: 4D Face Reconstruction from Any Image Sequence Transformer model for 4D face reconstruction and dense tracking: - predict canonical facial coordinates per pixel - tracking as reconstruction in canonical space - geometry + correspondences in one forward pass Key idea: a shared canonical space across frames - correspondences as nearest neighbors - no motion or deformation estimation Stable geometry and tracking, even under large expressions and viewpoint changes - check out our results! 🌐 ▶️ Great work by Umut Kocasarı, Simon Giebenhain, Richard Shaw

Matthias Niessner

61,636 views • 3 months ago

3D hand tracking on smart glasses Not only can we stream camera data with our Wearables SDK, but we can run MediaPipe for hand tracking, applying it in WebXR environments like Three.js and A-Frame Works with compatible smart glasses, in this case the Omi AI Omi Glass, based on the Seeed Studio XIAO ESP32-S3 Sense (running our custom Firmware)

3D hand tracking on smart glasses Not only can we stream camera data with our Wearables SDK, but we can run MediaPipe for hand tracking, applying it in WebXR environments like Three.js and A-Frame Works with compatible smart glasses, in this case the Omi AI Omi Glass, based on the Seeed Studio XIAO ESP32-S3 Sense (running our custom Firmware)

Brilliant Wear

79,540 views • 7 months ago

From 48 World Cup nations to an interactive 3D flower world. Tripo turns each nation into photorealistic 3D flowers, each designed with its own form, color palette, material texture, and cultural reference, and brings them into an interactive experience with GPT-5.5. The full collection is interactive, so every flower can be viewed, rotated, and explored in 3D. Tripo AI turns ideas into 3D experiences you can actually see, share, and explore.

From 48 World Cup nations to an interactive 3D flower world. Tripo turns each nation into photorealistic 3D flowers, each designed with its own form, color palette, material texture, and cultural reference, and brings them into an interactive experience with GPT-5.5. The full collection is interactive, so every flower can be viewed, rotated, and explored in 3D. Tripo AI turns ideas into 3D experiences you can actually see, share, and explore.

Tripo

13,143 views • 1 month ago