Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

Relightable Real-Time Avatars Meta Codec Avatars 2.0 gets an update, building on 3D Gaussian Splatting from Meta. Accuracy is down to the human hair strand level 🔬 🧵 A thread

351,889 Aufrufe • vor 2 Jahren •via X (Twitter)

10 Kommentare

Profilbild von Linus Ekenstam – eu/acc
Linus Ekenstam – eu/accvor 2 Jahren

Lighting It's impressive how this is done in real-time, and shows just how powerful Gaussian splats are.

Profilbild von Linus Ekenstam – eu/acc
Linus Ekenstam – eu/accvor 2 Jahren

View

Profilbild von Linus Ekenstam – eu/acc
Linus Ekenstam – eu/accvor 2 Jahren

Gaze

Profilbild von Linus Ekenstam – eu/acc
Linus Ekenstam – eu/accvor 2 Jahren

Expression

Profilbild von Linus Ekenstam – eu/acc
Linus Ekenstam – eu/accvor 2 Jahren

More examples of real-time avatars.

Profilbild von Linus Ekenstam – eu/acc
Linus Ekenstam – eu/accvor 2 Jahren

Here is the full video

Profilbild von Linus Ekenstam – eu/acc
Linus Ekenstam – eu/accvor 2 Jahren

Read the entire thing, and check out the project.

Profilbild von Linus Ekenstam – eu/acc
Linus Ekenstam – eu/accvor 2 Jahren

If you found this interesting and want more AI content directly in your inbox, sign up for my weekly free newsletter below.

Profilbild von Linus Ekenstam – eu/acc
Linus Ekenstam – eu/accvor 2 Jahren

If you enjoyed this content, please consider. 1. Follow me at @LinusEkenstam 2. Re-post/like or share this post with a friend

Profilbild von Adam ᯅ
Adam ᯅvor 2 Jahren

Amazing gives me Star Wars vibes

Ähnliche 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 Aufrufe • vor 2 Jahren