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.

Meet 3D Gaussian Splatting - a 3D AI breakthrough that’s changing the game for real-time 3D rendering. It generates 3D world with state-of-the-art visuals at fast speeds: 100+ fps at 1080p. Here’s the magic behind it:

el.cine

131,450 subscribers

60,115 views • 1 year ago •via X (Twitter)

Education Science & Technology

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

F3D-Gaus: Feed-forward 3D-aware Generation on ImageNet with Cycle-Consistent Gaussian Splatting Contributions: • We pioneer 3D-aware generation using generalizable feed-forward Gaussian Splatting representation, achieving significant efficiency and favorable rendering quality on monocular datasets. • We significantly advance the capability of pixel-aligned Gaussian Splatting representations by designing a self-supervised cycle training strategy specifically tailored for monocular datasets. • We further mitigate the artifacts of 3D-aware representations caused by large viewpoint shifts by introducing geometry-aware video priors.

F3D-Gaus: Feed-forward 3D-aware Generation on ImageNet with Cycle-Consistent Gaussian Splatting Contributions: • We pioneer 3D-aware generation using generalizable feed-forward Gaussian Splatting representation, achieving significant efficiency and favorable rendering quality on monocular datasets. • We significantly advance the capability of pixel-aligned Gaussian Splatting representations by designing a self-supervised cycle training strategy specifically tailored for monocular datasets. • We further mitigate the artifacts of 3D-aware representations caused by large viewpoint shifts by introducing geometry-aware video priors.

MrNeRF

14,229 views • 1 year 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

633,674 views • 3 years ago

woww.. AI can literally do 3D rendering now just upload a draft 3D animation, it turns it into cinematic film scene you can control the looks of the car and environment with image refs no need days of rendering anymore..

woww.. AI can literally do 3D rendering now just upload a draft 3D animation, it turns it into cinematic film scene you can control the looks of the car and environment with image refs no need days of rendering anymore..

el.cine

113,301 views • 8 months ago

Fairly certain these shots from the latest MrBeast video use 3D Gaussian Splatting! Cool to see it out in the wild.

Fairly certain these shots from the latest MrBeast video use 3D Gaussian Splatting! Cool to see it out in the wild.

Andrew Price

81,543 views • 2 months ago

Gaussian splats don't simulate light. They capture it. I took one photograph of this room and generated it as a fully walkable 3D world in Mint. The volumetric rays, the shadow play on the rug, all preserved. This is what real-time 3D is becoming

Gaussian splats don't simulate light. They capture it. I took one photograph of this room and generated it as a fully walkable 3D world in Mint. The volumetric rays, the shadow play on the rug, all preserved. This is what real-time 3D is becoming

mint

15,446 views • 2 months ago

Apple just trained a 3D Gaussian head reconstruction model on 10,000+ subjects. Feed-forward. No test-time optimization. New identity in, reconstructed Gaussian head out. The UV-parameterized Gaussian representation decouples the number of Gaussians from the number and resolution of input images, making it practical to train with many high resolution views. And the heads are not just static either: text-conditioned identity generation, plus blendshape-driven latent animation across identities. We've been building in the 3D Gaussian Splatting space for a while. The gap between "research demo" and "works on real people at scale" is closing fast.

Apple just trained a 3D Gaussian head reconstruction model on 10,000+ subjects. Feed-forward. No test-time optimization. New identity in, reconstructed Gaussian head out. The UV-parameterized Gaussian representation decouples the number of Gaussians from the number and resolution of input images, making it practical to train with many high resolution views. And the heads are not just static either: text-conditioned identity generation, plus blendshape-driven latent animation across identities. We've been building in the 3D Gaussian Splatting space for a while. The gap between "research demo" and "works on real people at scale" is closing fast.

KIRI Engine - 3D Scanner App

12,181 views • 3 months ago

Coding some WebGL shaders for 3D Gaussian Splatting 😀 Check the quality of clothes at 9 seconds! We are going to push things for fashion. live demo :

Coding some WebGL shaders for 3D Gaussian Splatting 😀 Check the quality of clothes at 9 seconds! We are going to push things for fashion. live demo :

Alexandre Devaux

327,048 views • 2 years ago

But what about hair? Dynamic 3D Gaussian Splatting can impressively reconstruct it. I find it fascinating how accurately a bunch of ellipsoids can capture the complexity of hair. Amazing!

But what about hair? Dynamic 3D Gaussian Splatting can impressively reconstruct it. I find it fascinating how accurately a bunch of ellipsoids can capture the complexity of hair. Amazing!

MrNeRF

30,623 views • 1 year ago

The #1 AI 3D Model Generator just got a game-changing upgrade — and anyone can use it. No 3D design experience? No problem. From game assets to product design — this tool does it all. 👇🧵

The #1 AI 3D Model Generator just got a game-changing upgrade — and anyone can use it. No 3D design experience? No problem. From game assets to product design — this tool does it all. 👇🧵

Md Riyazuddin

286,879 views • 1 year ago

I made a 3D Gaussian Splatting renderer for WebGL! The following scene renders 1.3M splats in real time. I wanted to understand a bit more how gaussian splats were rasterized, reimplementing the original paper seemed to be the best approach. I will publish it on github soon!

I made a 3D Gaussian Splatting renderer for WebGL! The following scene renders 1.3M splats in real time. I wanted to understand a bit more how gaussian splats were rasterized, reimplementing the original paper seemed to be the best approach. I will publish it on github soon!

kishimisu

84,532 views • 2 years 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

11,520 views • 9 months ago

Real-time generation isn’t about predicting the next pixel, it requires understanding the structure and context of a 3D world. That’s the shift. Read more about our real-time game-native diffusion model on our blog. Moonlake's Reverie v0.1.0

Real-time generation isn’t about predicting the next pixel, it requires understanding the structure and context of a 3D world. That’s the shift. Read more about our real-time game-native diffusion model on our blog. Moonlake's Reverie v0.1.0

Moonlake

14,439 views • 8 months ago

Oh wow! I just tested Splatt3R with my own data on my computer, which creates 3D Gaussian Splats at 4 FPS on uncalibrated 512x512 2D images! It's by far the fastest 3D reconstruction method, powered by MASt3R. Check out the video!

Oh wow! I just tested Splatt3R with my own data on my computer, which creates 3D Gaussian Splats at 4 FPS on uncalibrated 512x512 2D images! It's by far the fastest 3D reconstruction method, powered by MASt3R. Check out the video!

MrNeRF

68,940 views • 2 years ago

Many 3D generators output Gaussian Splats (3DGS) for fast rendering, flexible deployment, and high visual fidelity. Static 3DGS aren't world models (no dynamics/semantics) but a true world model must allow distilling 3D-consistent representations for any given time step (3DGS/meshes). This post-distillation serves a dual purpose: 1) validates physical consistency of the model. 2) extracting explicit representations avoids continuously running a heavy generator, thus saves compute and facilitates real-time interaction.

Many 3D generators output Gaussian Splats (3DGS) for fast rendering, flexible deployment, and high visual fidelity. Static 3DGS aren't world models (no dynamics/semantics) but a true world model must allow distilling 3D-consistent representations for any given time step (3DGS/meshes). This post-distillation serves a dual purpose: 1) validates physical consistency of the model. 2) extracting explicit representations avoids continuously running a heavy generator, thus saves compute and facilitates real-time interaction.

Matthias Niessner

26,416 views • 5 months ago

(1/3) 📢📢𝐆𝐆𝐇𝐞𝐚𝐝 𝐅𝐚𝐬𝐭 𝐚𝐧𝐝 𝐆𝐞𝐧𝐞𝐫𝐚𝐥𝐢𝐳𝐚𝐛𝐥𝐞 𝟑𝐃 𝐆𝐚𝐮𝐬𝐬𝐢𝐚𝐧 𝐇𝐞𝐚𝐝𝐬📢📢 #SiggraphAsia'24 We generate photo-realistic 3D heads and render them with Gaussian Splatting at 1k resolution in real-time.

(1/3) 📢📢𝐆𝐆𝐇𝐞𝐚𝐝 𝐅𝐚𝐬𝐭 𝐚𝐧𝐝 𝐆𝐞𝐧𝐞𝐫𝐚𝐥𝐢𝐳𝐚𝐛𝐥𝐞 𝟑𝐃 𝐆𝐚𝐮𝐬𝐬𝐢𝐚𝐧 𝐇𝐞𝐚𝐝𝐬📢📢 #SiggraphAsia'24 We generate photo-realistic 3D heads and render them with Gaussian Splatting at 1k resolution in real-time.

Matthias Niessner

36,618 views • 1 year ago

1/ 🌌 Roblox isn't just a video game — it's the world's largest UGC 3D platform. But wait, it gets better! 🧙‍♂️ Roblox is now embracing Generative AI, shattering barriers to 3D creation, and creating a TikTok-like flywheel 🔁 🧵 Thread: here's how the magic is unfolding in 3D 🪄

1/ 🌌 Roblox isn't just a video game — it's the world's largest UGC 3D platform. But wait, it gets better! 🧙‍♂️ Roblox is now embracing Generative AI, shattering barriers to 3D creation, and creating a TikTok-like flywheel 🔁 🧵 Thread: here's how the magic is unfolding in 3D 🪄

Bilawal Sidhu

393,688 views • 3 years ago

DroneSplat: 3D Gaussian Splatting for Robust 3D Reconstruction from In-the-Wild Drone Imagery Abstract: Drones have become essential tools for reconstructing wild scenes due to their outstanding maneuverability. Recent advances in radiance field methods have achieved remarkable rendering quality, providing a new avenue for 3D reconstruction from drone imagery. However, dynamic distractors in wild environments challenge the static scene assumption in radiance fields, while limited view constraints hinder the accurate capture of underlying scene geometry. To address these challenges, we introduce DroneSplat, a novel framework designed for robust 3D reconstruction from in-the-wild drone imagery. Our method adaptively adjusts masking thresholds by integrating local-global segmentation heuristics with statistical approaches, enabling precise identification and elimination of dynamic distractors in static scenes. We enhance 3D Gaussian Splatting with multi-view stereo predictions and a voxel-guided optimization strategy, supporting high-quality rendering under limited view constraints. For comprehensive evaluation, we provide a drone-captured 3D reconstruction dataset encompassing both dynamic and static scenes. Extensive experiments demonstrate that DroneSplat outperforms both 3DGS and NeRF baselines in handling in-the-wild drone imagery.

DroneSplat: 3D Gaussian Splatting for Robust 3D Reconstruction from In-the-Wild Drone Imagery Abstract: Drones have become essential tools for reconstructing wild scenes due to their outstanding maneuverability. Recent advances in radiance field methods have achieved remarkable rendering quality, providing a new avenue for 3D reconstruction from drone imagery. However, dynamic distractors in wild environments challenge the static scene assumption in radiance fields, while limited view constraints hinder the accurate capture of underlying scene geometry. To address these challenges, we introduce DroneSplat, a novel framework designed for robust 3D reconstruction from in-the-wild drone imagery. Our method adaptively adjusts masking thresholds by integrating local-global segmentation heuristics with statistical approaches, enabling precise identification and elimination of dynamic distractors in static scenes. We enhance 3D Gaussian Splatting with multi-view stereo predictions and a voxel-guided optimization strategy, supporting high-quality rendering under limited view constraints. For comprehensive evaluation, we provide a drone-captured 3D reconstruction dataset encompassing both dynamic and static scenes. Extensive experiments demonstrate that DroneSplat outperforms both 3DGS and NeRF baselines in handling in-the-wild drone imagery.

MrNeRF

21,346 views • 1 year ago

Damn it worked! Genie 3 world --> inpaint UI --> 4x topaz AI upscale --> train 3d gaussian splat You can step inside a painting of Socrates from 1787. Better than any image-to-3d model I've seen. I think Google has stumbled upon the killer app for VR -- the literal holodeck.

Damn it worked! Genie 3 world --> inpaint UI --> 4x topaz AI upscale --> train 3d gaussian splat You can step inside a painting of Socrates from 1787. Better than any image-to-3d model I've seen. I think Google has stumbled upon the killer app for VR -- the literal holodeck.

Bilawal Sidhu

658,477 views • 1 year ago