Loading video...

Video Failed to Load

Go Home

3D was either pretty, or fast. Now it’s BOTH! Meet Interactive Scenes built with Gaussian Splatting: 🔥Browser & Phone-Friendly: Hyperefficient and fast rendering everywhere 👌Embed Anywhere: 8-20MB streaming files (even smaller soon!) ✨Ultra High Quality offline NeRF renders & mesh exports 🍕Creating is as easy as capturing a video...

528,667 views • 2 years ago •via X (Twitter)

10 Comments

Luma AI's profile picture
Luma AI2 years ago

⬆️Upgrade your best Luma captures to Interactive Scenes right in the app or on the web ✨And now, export UE and Splat files as well

Luma AI's profile picture
Luma AI2 years ago

Congratulations to @Snosixtytwo and @GKopanas, and INRIA for their incredible research on realtime 3D rendering!

Luma AI's profile picture
Luma AI2 years ago

Meet the spectacular new Metal 3D renderer! It's fast, beautiful, and so much fun to play with!

Luma AI's profile picture
Luma AI2 years ago

Meet the hyperefficient new WebGL renderer. It just _flies_ on phones old and new, and screams on laptops! Feat an intricate but kind humanoid by @ryanmhickman

Luma AI's profile picture
Luma AI2 years ago

Let’s bring Interactive Scenes everywhere!

Alex Carlier's profile picture
Alex Carlier2 years ago

Amazing work! Will try some captures asap 🔥🙌

polycam's profile picture
polycam2 years ago

Welcome to the club!

Martin Nebelong's profile picture
Martin Nebelong2 years ago

Incredible, can't wait to experiment with this 🔥❤️

bloomy 🌸's profile picture
bloomy 🌸2 years ago

i never thought the future would come this fast fr

Jon Booth 🧙‍♂️'s profile picture
Jon Booth 🧙‍♂️2 years ago

So you’re telling me soon we can build 3D sets and literally be digital directors and create anything… or is this the Now? Holy

Related Videos

Nvidia announces GAvatar: Animatable 3D Gaussian Avatars with Implicit Mesh Learning paper page: Gaussian splatting has emerged as a powerful 3D representation that harnesses the advantages of both explicit (mesh) and implicit (NeRF) 3D representations. In this paper, we seek to leverage Gaussian splatting to generate realistic animatable avatars from textual descriptions, addressing the limitations (e.g., flexibility and efficiency) imposed by mesh or NeRF-based representations. However, a naive application of Gaussian splatting cannot generate high-quality animatable avatars and suffers from learning instability; it also cannot capture fine avatar geometries and often leads to degenerate body parts. To tackle these problems, we first propose a primitive-based 3D Gaussian representation where Gaussians are defined inside pose-driven primitives to facilitate animation. Second, to stabilize and amortize the learning of millions of Gaussians, we propose to use neural implicit fields to predict the Gaussian attributes (e.g., colors). Finally, to capture fine avatar geometries and extract detailed meshes, we propose a novel SDF-based implicit mesh learning approach for 3D Gaussians that regularizes the underlying geometries and extracts highly detailed textured meshes. Our proposed method, GAvatar, enables the large-scale generation of diverse animatable avatars using only text prompts. GAvatar significantly surpasses existing methods in terms of both appearance and geometry quality, and achieves extremely fast rendering (100 fps) at 1K resolution.

AK

140,960 views • 2 years ago