Loading video...

Video Failed to Load

Go Home

Code release: "PhysGaussian: Physics-Integrated 3D Gaussians for Generative Dynamics"

janusch_patas's profile picture

MrNeRF

16,878 subscribers

29,976 views • 2 years ago •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Built a cool 3D physics receipt using Gemini. Grab the code below ⤵️
0:12

Built a cool 3D physics receipt using Gemini. Grab the code below ⤵️

Oogie

50,304 views • 6 months ago

Introducing Generative UI for Claude Code, Codex and Pi Charts, forms, 3D, anything Your agent renders real UI for users while it works in a sandbox Powered by AI SDK's experimental HarnessAgent + json-render
0:14

Introducing Generative UI for Claude Code, Codex and Pi Charts, forms, 3D, anything Your agent renders real UI for users while it works in a sandbox Powered by AI SDK's experimental HarnessAgent + json-render

Chris Tate

171,026 views • 3 months 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!
0:14

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

Adobe continues the integration of Firefly in the Adobe Substance 3D ecosystem with two new AI-based features added to 3D Sampler Beta and Generative Background now available in the stable release of 3D Stager. Learn more: #adobe #3dsampler #3dstager
0:15

Adobe continues the integration of Firefly in the Adobe Substance 3D ecosystem with two new AI-based features added to 3D Sampler Beta and Generative Background now available in the stable release of 3D Stager. Learn more: #adobe #3dsampler #3dstager

80 LEVEL

11,923 views • 2 years ago

🚀 A new Visual Studio Code weekly release is here! One of our favorite features is integrated browser debugging, which lets you debug your web app end-to-end without leaving the editor.
0:14

🚀 A new Visual Studio Code weekly release is here! One of our favorite features is integrated browser debugging, which lets you debug your web app end-to-end without leaving the editor.

Visual Studio Code

137,218 views • 6 months ago

GSTAR: Gaussian Surface Tracking and Reconstruction Contributions: • A new framework for tracking and reconstructing dynamic scenes, combining 3D Gaussians and meshes to effectively manage changes in topology. • A method for Gaussian unbinding and surface re-meshing, allowing for the generation of new surfaces as topologies evolve. • A method for handling large or fast deformations of surfaces between frames using scene flow warping. Abstract (excerpt): However, tracking dynamic surfaces with 3D Gaussians remains challenging due to complex topology changes, such as surfaces appearing, disappearing, or splitting. To address these challenges, we propose GSTAR, a novel method that achieves photo-realistic rendering, accurate surface reconstruction, and reliable 3D tracking for general dynamic scenes with changing topology. Given multi-view captures as input, GSTAR binds Gaussians to mesh faces to represent dynamic objects. For surfaces with consistent topology, GSTAR maintains the mesh topology and tracks the meshes using Gaussians.
0:13

GSTAR: Gaussian Surface Tracking and Reconstruction Contributions: • A new framework for tracking and reconstructing dynamic scenes, combining 3D Gaussians and meshes to effectively manage changes in topology. • A method for Gaussian unbinding and surface re-meshing, allowing for the generation of new surfaces as topologies evolve. • A method for handling large or fast deformations of surfaces between frames using scene flow warping. Abstract (excerpt): However, tracking dynamic surfaces with 3D Gaussians remains challenging due to complex topology changes, such as surfaces appearing, disappearing, or splitting. To address these challenges, we propose GSTAR, a novel method that achieves photo-realistic rendering, accurate surface reconstruction, and reliable 3D tracking for general dynamic scenes with changing topology. Given multi-view captures as input, GSTAR binds Gaussians to mesh faces to represent dynamic objects. For surfaces with consistent topology, GSTAR maintains the mesh topology and tracks the meshes using Gaussians.

MrNeRF

22,698 views • 1 year ago

which tutorial (+code) should I release next? > Left: 3D graph data viz > Right: Severance game projects are built with Three.js and mediapipe AI vision learn how to build real-time hand tracking apps for 3D design, games, etc.
0:12

which tutorial (+code) should I release next? > Left: 3D graph data viz > Right: Severance game projects are built with Three.js and mediapipe AI vision learn how to build real-time hand tracking apps for 3D design, games, etc.

AA

19,435 views • 1 year ago

Researchers are exploring Marble’s generative 3D worlds as a way to rapidly produce simulation-ready environments for robotics without manual scene construction.
0:18

Researchers are exploring Marble’s generative 3D worlds as a way to rapidly produce simulation-ready environments for robotics without manual scene construction.

World Labs

73,441 views • 10 months 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.
0:13

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

106,653 views • 2 years ago

Sketch2Pose for Blender makes it easy to turn rough sketches into 3D poses from different camera angles, with no generative AI involved. Now available at 25% off:
0:14

Sketch2Pose for Blender makes it easy to turn rough sketches into 3D poses from different camera angles, with no generative AI involved. Now available at 25% off:

80 LEVEL

53,577 views • 12 days ago

[C] Fresh Fresh emote from Fortnite for ALL - comes w/wo music - realistic skirt, tail, and bust physics Commissioned for free public release!
0:15

[C] Fresh Fresh emote from Fortnite for ALL - comes w/wo music - realistic skirt, tail, and bust physics Commissioned for free public release!

raykie

71,008 views • 3 years ago

📢📢📢 Check out XCube, a generative model for very-high resolution 3D shapes and scenes! Project Page: Project Video: Props to Xuanchi Ren for leading this project!!!! [1/N]
0:14

📢📢📢 Check out XCube, a generative model for very-high resolution 3D shapes and scenes! Project Page: Project Video: Props to Xuanchi Ren for leading this project!!!! [1/N]

Francis Williams

42,417 views • 2 years ago

Harness the power of generative AI without just prompting and hoping for the best. From Unbound Slop to Tripo🔜SIGGRAPH2026 to Unreal Engine, we love this workflow for generating 3D models.
0:17

Harness the power of generative AI without just prompting and hoping for the best. From Unbound Slop to Tripo🔜SIGGRAPH2026 to Unreal Engine, we love this workflow for generating 3D models.

Unbound

26,532 views • 5 months ago

made a 3d model of character of Team Reptile BRC excited for Game release 💥
0:15

made a 3d model of character of Team Reptile BRC excited for Game release 💥

zip

62,115 views • 3 years ago

Ah yeah, just me trying to vibe code something new every day :D That 3D Rubik’s Cube you see there is built from scratch (custom math-based physics engine) using Three.js with GSAP animations and totally vibe coded in Google AI Studio using Gemini 3 Pro AI. Live: Code:
0:18

Ah yeah, just me trying to vibe code something new every day :D That 3D Rubik’s Cube you see there is built from scratch (custom math-based physics engine) using Three.js with GSAP animations and totally vibe coded in Google AI Studio using Gemini 3 Pro AI. Live: Code:

The Bugged Dev

71,922 views • 8 months ago

📢🚗✨ Excited to announce InfiniCube, our scalable generative model for dynamic 3D driving scene generation with high fidelity and controllability! InfiniCube generates very large-scale (300m×400m ~ 100,000m^2), dynamic 3D driving scenes given HD maps, 3D bounding boxes, and text prompts as controls. Website: Props to Yifan Lu for leading this project!!!! [1/N]
0:16

📢🚗✨ Excited to announce InfiniCube, our scalable generative model for dynamic 3D driving scene generation with high fidelity and controllability! InfiniCube generates very large-scale (300m×400m ~ 100,000m^2), dynamic 3D driving scenes given HD maps, 3D bounding boxes, and text prompts as controls. Website: Props to Yifan Lu for leading this project!!!! [1/N]

Xuanchi Ren

26,638 views • 1 year ago

🪄 ChatGPT-5 Magic!🪄 I took the classic AI coding challenge into full 3D with our upcoming #FigminXR API — and my mind is blown 🤯 My AI built the 3D models using our Tilt Brush tools and brought them to life with it's *OWN* physics simulation! Code in the comments ⬇️
0:14

🪄 ChatGPT-5 Magic!🪄 I took the classic AI coding challenge into full 3D with our upcoming #FigminXR API — and my mind is blown 🤯 My AI built the 3D models using our Tilt Brush tools and brought them to life with it's *OWN* physics simulation! Code in the comments ⬇️

Javier Davalos

17,686 views • 1 year ago

Excited to announce that Hand Physics Lab got reviewed and approved for release on Vision Pro! 😃 Something imminent is coming! 👀🙌
0:13

Excited to announce that Hand Physics Lab got reviewed and approved for release on Vision Pro! 😃 Something imminent is coming! 👀🙌

Dennys Kuhnert

27,996 views • 1 year ago