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.

🔥 We also open-source a UE5-based data engine, which help reproduce research works in 3D/4D reconstruction. 4D Data Engine:

Tengfei Wang

3,679 subscribers

18,695 views • 29 days 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

Introducing Make-A-Video3D! Generating 3D dynamic (mini) scenes from input text. That is, text --> 4D! Needs no 4D data (i.e., no dynamic 3D data), no static 3D data, no paired text-video data. Paper: Website:

Introducing Make-A-Video3D! Generating 3D dynamic (mini) scenes from input text. That is, text --> 4D! Needs no 4D data (i.e., no dynamic 3D data), no static 3D data, no paired text-video data. Paper: Website:

Devi Parikh

305,729 views • 3 years ago

A RAG engine for deep document understanding! RAGFlow lets you build enterprise-grade RAG workflows on complex docs with well-founded citations. Supports multimodal data understanding, web search, deep research, etc. 100% local & open-source with 55k+ stars!

A RAG engine for deep document understanding! RAGFlow lets you build enterprise-grade RAG workflows on complex docs with well-founded citations. Supports multimodal data understanding, web search, deep research, etc. 100% local & open-source with 55k+ stars!

Avi Chawla

163,773 views • 1 year ago

Alpha testing is crucial, and with the real-time heatmap we've developed in #UE5, our alpha map for #RootedTheGame is providing instantaneous data. Refining gameplay has never been this dynamic! #survival #indiegame #gamedev Unreal Engine

Alpha testing is crucial, and with the real-time heatmap we've developed in #UE5, our alpha map for #RootedTheGame is providing instantaneous data. Refining gameplay has never been this dynamic! #survival #indiegame #gamedev Unreal Engine

Rooted • Post-apo Survival Game

26,571 views • 2 years 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

Stadium-scale, studio-quality motion capture is launching soon… Full 3D control, stable bone lengths and realistic ground-foot contact for high-fidelity animation in Unreal Engine, Blender or any 3D engine. This is not pose estimation—this is dynamic, high-precision, real-world data capturing at AAA quality, providing you with lifelike avatars and seamless animation like never before. 📷⚽️

Stadium-scale, studio-quality motion capture is launching soon… Full 3D control, stable bone lengths and realistic ground-foot contact for high-fidelity animation in Unreal Engine, Blender or any 3D engine. This is not pose estimation—this is dynamic, high-precision, real-world data capturing at AAA quality, providing you with lifelike avatars and seamless animation like never before. 📷⚽️

Move AI

67,319 views • 1 year ago

The power of data-driven spectral submanifold (SSM) reduction: Nonlinear oscillations of an elastic flag in counter flow, together with its reconstructed chaotic attractor within a 4D SSM. Obtained directly from the videos of the experiment.

The power of data-driven spectral submanifold (SSM) reduction: Nonlinear oscillations of an elastic flag in counter flow, together with its reconstructed chaotic attractor within a 4D SSM. Obtained directly from the videos of the experiment.

George Haller

88,417 views • 2 years ago

Human Hair Reconstruction with Strand-Aligned 3D Gaussians Contributions (cited): – We propose a new 3D line lifting scheme that uses a modified 3DGS reconstruction technique to lift 2D orientation maps into a 3D field while also providing refinement of the camera parameters; – We introduce a dual representation of hair strand polylines and 3D Gaussians to achieve differentiable rasterization of hair strands and leverage photometric constraints for strand-based hair reconstruction; – Based on these components, we propose a coarse-to-fine optimization method for prior-guided hair reconstruction that leverages both latent and explicit representations of the hairstyle.

Human Hair Reconstruction with Strand-Aligned 3D Gaussians Contributions (cited): – We propose a new 3D line lifting scheme that uses a modified 3DGS reconstruction technique to lift 2D orientation maps into a 3D field while also providing refinement of the camera parameters; – We introduce a dual representation of hair strand polylines and 3D Gaussians to achieve differentiable rasterization of hair strands and leverage photometric constraints for strand-based hair reconstruction; – Based on these components, we propose a coarse-to-fine optimization method for prior-guided hair reconstruction that leverages both latent and explicit representations of the hairstyle.

MrNeRF

106,525 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

36,950 views • 5 months ago

This is PopcornFX, a 3rd party VFX tool. Godot Engine plugin coming soon. - Custom plugin run, not tied to Godot particle system - Exposed parameters in engine - Works with Godot materials - Node based editor A whole new way to create particle effects for Godot.

This is PopcornFX, a 3rd party VFX tool. Godot Engine plugin coming soon. - Custom plugin run, not tied to Godot particle system - Exposed parameters in engine - Works with Godot materials - Node based editor A whole new way to create particle effects for Godot.

StayAtHomeDev - Making Children of Kronos

12,049 views • 5 months ago

10 years of "it can't be done..." 7 NVIDIA GPU architectures... 5 years of RAPIDS AI... 3 years of Voltron Data... finally a petabyte-scale GPU-native engine that DOESN'T require you to change your data pipelines. Same code, same data formats, just modular, interoperable, composable, extensible... and of course ACCELERATED! Theseus is the Scalable Performant And Compute Efficient engine🔥🔥🔥 Check out our benchmarks and new webpage... and reach out if you're struggling with queries above 30TBs.

10 years of "it can't be done..." 7 NVIDIA GPU architectures... 5 years of RAPIDS AI... 3 years of Voltron Data... finally a petabyte-scale GPU-native engine that DOESN'T require you to change your data pipelines. Same code, same data formats, just modular, interoperable, composable, extensible... and of course ACCELERATED! Theseus is the Scalable Performant And Compute Efficient engine🔥🔥🔥 Check out our benchmarks and new webpage... and reach out if you're struggling with queries above 30TBs.

Josh Patterson

17,000 views • 2 years ago

Someone open-sourced GeoLibre, a free DuckDB-WASM 3D spatial mapping engine that runs GIS analytics for Earth and space directly in your browser.

Someone open-sourced GeoLibre, a free DuckDB-WASM 3D spatial mapping engine that runs GIS analytics for Earth and space directly in your browser.

0xMarioNawfal

60,461 views • 16 days ago

A view of how the fake-3d parallax works in my game Well Dweller. The game engine I use is primarily for 2D games (gamemaker), so I instead have background objects lean with the camera position based on their assigned depth

A view of how the fake-3d parallax works in my game Well Dweller. The game engine I use is primarily for 2D games (gamemaker), so I instead have background objects lean with the camera position based on their assigned depth

Kyle Thompson (Wishlist WELL DWELLER on Steam!)

64,268 views • 6 months ago

3D Elevation Maps Draw anywhere on a map to render interactive 3D terrain. Adjust height, add contours, and download models or data. Great open source tool to explore landscapes (by Jonathan Callura): worldviewr .com

3D Elevation Maps Draw anywhere on a map to render interactive 3D terrain. Adjust height, add contours, and download models or data. Great open source tool to explore landscapes (by Jonathan Callura): worldviewr .com

Leon

37,759 views • 11 months ago

Unity is integrating AI and shifting the responsibility for any infringement onto users Anyway here’s a game I made in the open-source engine Godot

Unity is integrating AI and shifting the responsibility for any infringement onto users Anyway here’s a game I made in the open-source engine Godot

guselect

27,621 views • 11 months ago

A Tesseract is the 4D extension of a cube, just as a cube is the 3D extension of a square. While we live in a three dimensional world, mathematics allows us to describe shapes that exist in higher dimensions.

A Tesseract is the 4D extension of a cube, just as a cube is the 3D extension of a square. While we live in a three dimensional world, mathematics allows us to describe shapes that exist in higher dimensions.

Science Simplified

59,554 views • 2 months ago

If you'd like to get started with Godot Engine, check out one of my Starter Kits. Open source projects with bare minimum set-ups for a 3D platformer, FPS and city building game! More coming...

If you'd like to get started with Godot Engine, check out one of my Starter Kits. Open source projects with bare minimum set-ups for a 3D platformer, FPS and city building game! More coming...

Kenney

70,507 views • 2 years ago

We wired 3D Gaussian Splatting into the 1999 Quake 3 engine - it's fully playable! Echo-2 generates the game levels, and it's rendering spaces directly inside the open source version of id Tech 3. Anyone wants to try it?

We wired 3D Gaussian Splatting into the 1999 Quake 3 engine - it's fully playable! Echo-2 generates the game levels, and it's rendering spaces directly inside the open source version of id Tech 3. Anyone wants to try it?

SpAItial AI

16,624 views • 3 months ago

bars, vision, and a creative engine that doesn’t quit 🔥 welcome SKRYU to the #Foundry Class of 2025! in his own words: “YouTube is a core engine for me—the essential source that powers my creativity and daily life.” we can’t wait to see what he builds next

bars, vision, and a creative engine that doesn’t quit 🔥 welcome SKRYU to the #Foundry Class of 2025! in his own words: “YouTube is a core engine for me—the essential source that powers my creativity and daily life.” we can’t wait to see what he builds next

YouTube Music

20,517 views • 10 months ago

OpenAI's Deep Research is getting a run for its money. Deep Lake was just released, and it's a different take on an AI system that can do deep research on your own data. You can use Deep Lake to build AI search with reasoning on your private and public data. (Look at the attached videos to get an idea of how it works.) If you want to research proprietary and sensitive data, Deep Research won't help you because it's limited to public data. Deep Lake, however, will allow you to use your private data. On top of that, Deep Lake supports multi-modal retrieval from the ground up. It uses vision language models for data ingestion and retrieval so that you can connect any data (PDFs, images, videos, structured data, etc.) You can even use mixed-data queries! Deep Lake can search your data from S3, Dropbox, and GCP. It learns from your queries over time, making the results as relevant to your work as possible!

OpenAI's Deep Research is getting a run for its money. Deep Lake was just released, and it's a different take on an AI system that can do deep research on your own data. You can use Deep Lake to build AI search with reasoning on your private and public data. (Look at the attached videos to get an idea of how it works.) If you want to research proprietary and sensitive data, Deep Research won't help you because it's limited to public data. Deep Lake, however, will allow you to use your private data. On top of that, Deep Lake supports multi-modal retrieval from the ground up. It uses vision language models for data ingestion and retrieval so that you can connect any data (PDFs, images, videos, structured data, etc.) You can even use mixed-data queries! Deep Lake can search your data from S3, Dropbox, and GCP. It learns from your queries over time, making the results as relevant to your work as possible!

Santiago

171,340 views • 1 year ago