Loading video...

Video Failed to Load

Go Home

demo combining gaussian splat rendering from spark with a collider mesh baked out from the gaussians, using rapier physics in Three.js

24,981 views • 1 year ago •via X (Twitter)

6 Comments

Ben Mildenhall's profile picture
Ben Mildenhall1 year ago

code @ mostly thanks to @cursor_ai :) try it @

Hugo Duprez's profile picture
Hugo Duprez1 year ago

@sparkjsdev @threejs Very cool! Played around something similar for FPS

Silicon Jungle's profile picture
Silicon Jungle1 year ago

@sparkjsdev @threejs pretty cool

Vincent Woo's profile picture
Vincent Woo1 year ago

@sparkjsdev @threejs Any tips for baking meshes from gaussians?

Doeon Kwon's profile picture
Doeon Kwon1 year ago

@sparkjsdev @threejs this so cool, I gotta try it asap to my product

Wyrd's profile picture
Wyrd1 year ago

@sparkjsdev @threejs

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

140,992 views • 2 years ago