Загрузка видео...

Не удалось загрузить видео

На главную

HoloDreamer can generate enclosed 3D scenes from text descriptions! It does so by first creating a high-quality equirectangular panorama and then rapidly reconstructing the 3D scene using 3D Gaussian Splatting. Links ⬇️

59,361 просмотров • 1 год назад •via X (Twitter)

Комментарии: 10

Фото профиля Dreaming Tulpa 🥓👑
Dreaming Tulpa 🥓👑1 год назад

Project Page: Code:

Фото профиля maddie🌙
maddie🌙1 год назад

looks like pure shite, good work

Фото профиля Dennis
Dennis1 год назад

sick

Фото профиля Kiri
Kiri1 год назад

Wow!!!!

Фото профиля Charles Williamson
Charles Williamson1 год назад

This looks interesting!

Фото профиля Tang the Wandering Hermit
Tang the Wandering Hermit1 год назад

Man, roblox creator gonna be nuts lmao

Фото профиля 🤐
🤐1 год назад

惊艳!效果真好

Фото профиля Pseudonym 🦅
Pseudonym 🦅1 год назад

Lego as a benchmark is quite clever. It’s easy to spot differences and design consistency. Lego builds either look like Lego or are clearly wrong. Pretty incredible a non specialized system can even get this close. Reminds me of the whole fine tuning versus prompting debate.

Фото профиля Ericreator
Ericreator1 год назад

is the code live? i only saw a readme and lic

Фото профиля Dreaming Tulpa 🥓👑
Dreaming Tulpa 🥓👑1 год назад

Nope. Not live.

Похожие видео

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 просмотров • 2 лет назад