Loading video...

Video Failed to Load

Go Home

Direct3D‑S2: Gigascale 3D Generation Made Easy with Spatial Sparse Attention

dreamingtulpa's profile picture

Dreaming Tulpa 🥓👑

55,274 subscribers

27,799 views • 1 year 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

Wow with new #iPhone15 Pro we’ll be able to record 3d spatial videos! #AppleEvent
0:10

Wow with new #iPhone15 Pro we’ll be able to record 3d spatial videos! #AppleEvent

iJustine

226,330 views • 2 years ago

🔥Spatial intelligence needs fast, *interactive* 3D world generation 🎮 — introducing WonderWorld: generating 3D scenes interactively following your movement and content requests, and see them in <10 seconds! 🧵1/6 Web: arXiv:
0:10

🔥Spatial intelligence needs fast, *interactive* 3D world generation 🎮 — introducing WonderWorld: generating 3D scenes interactively following your movement and content requests, and see them in <10 seconds! 🧵1/6 Web: arXiv:

Hong-Xing (Koven) Yu

169,078 views • 1 year ago

🔥Spatial intelligence requires world generation, and now we have the first comprehensive evaluation benchmark📏 for it! Introducing WorldScore: Unifying evaluation for 3D, 4D, and video models on world generation! 🧵1/7 Web: arxiv:
0:14

🔥Spatial intelligence requires world generation, and now we have the first comprehensive evaluation benchmark📏 for it! Introducing WorldScore: Unifying evaluation for 3D, 4D, and video models on world generation! 🧵1/7 Web: arxiv:

Hong-Xing (Koven) Yu

66,615 views • 1 year ago

"Spann3R: 3D Reconstruction with Spatial Memory" In a nutshell: DUSt3R strikes again! Paper: Project: Method ⬇️
0:14

"Spann3R: 3D Reconstruction with Spatial Memory" In a nutshell: DUSt3R strikes again! Paper: Project: Method ⬇️

MrNeRF

52,560 views • 1 year ago

Gemini 3.1 is SOTA at 3D spatial reasoning
0:14

Gemini 3.1 is SOTA at 3D spatial reasoning

Zach Dive

196,182 views • 3 months ago

monocular vision is wild one camera stream, estimating motion and sparse 3D structure from changing pixels alone
0:17

monocular vision is wild one camera stream, estimating motion and sparse 3D structure from changing pixels alone

tetsuo

29,464 views • 1 month ago

"Physics of AI" blog update: Learning sparse attention has a sticky plateau, representation collapse, and branching dynamics
0:10

"Physics of AI" blog update: Learning sparse attention has a sticky plateau, representation collapse, and branching dynamics

Ziming Liu

81,746 views • 5 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.
0:18

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

17,017 views • 1 year ago

Turn regular photos into 3D Spatial photos on #iOS26 🤯 *Beta, coming to public from Autumn
0:18

Turn regular photos into 3D Spatial photos on #iOS26 🤯 *Beta, coming to public from Autumn

Safwan AhmedMia

27,999 views • 11 months ago

Spatial Scene feature looks awesome 🤩✨ Turn your regular 2D photos into 3D #iOS26 #WWDC25
0:15

Spatial Scene feature looks awesome 🤩✨ Turn your regular 2D photos into 3D #iOS26 #WWDC25

Ben Geskin

79,758 views • 1 year ago

Exploring !Boring stickers! in 3D, made with Omma.
0:13

Exploring !Boring stickers! in 3D, made with Omma.

Gábor Pribék

275,035 views • 22 days ago

This handy print makes magnet installation much easier! Made with: ELEGOO #CentauriCarbon 3D printer 3D model from: HX8 3D Design
0:16

This handy print makes magnet installation much easier! Made with: ELEGOO #CentauriCarbon 3D printer 3D model from: HX8 3D Design

ELEGOO

25,357 views • 6 months ago

Easy breakfast idea made with simple toaster bread
0:14

Easy breakfast idea made with simple toaster bread

Robust Feed

20,340 views • 1 month ago

Metal Repair Made Easy with This Magic Sealant
0:12

Metal Repair Made Easy with This Magic Sealant

Chill_Broken

1,488,674 views • 7 months ago

Long drives made easy with thot b!txh
0:10

Long drives made easy with thot b!txh

Midnighthugo

10,997 views • 10 months ago

hunting ghosts not made in 3D, but with AI
0:10

hunting ghosts not made in 3D, but with AI

INK

49,788 views • 4 months ago

Foldable donut made with Easy vertex anim plugin #UE5
0:19

Foldable donut made with Easy vertex anim plugin #UE5

Inu Games

61,793 views • 6 months ago

Easy 3D Art 😍 © condsty
0:13

Easy 3D Art 😍 © condsty

Sarahh

2,227,232 views • 10 months ago

iMac G3 icon - literally made with liquid 3D 🍎💧
0:13

iMac G3 icon - literally made with liquid 3D 🍎💧

Womp

25,692 views • 1 year ago

crazy.. AI made 3D Pixar animation with just one prompt
0:16

crazy.. AI made 3D Pixar animation with just one prompt

el.cine

3,473,702 views • 1 month ago