Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

This new AI tool is interesting! ReconX can create a 3D scene using just two images from different angles. Imagine if we could train our character with only 2 images instead of 10?

69,436 Aufrufe • vor 1 Jahr •via X (Twitter)

10 Kommentare

Profilbild von el.cine
el.cinevor 1 Jahr

Paper:

Profilbild von TomLikesRobots🤖
TomLikesRobots🤖vor 1 Jahr

Interesting that it's not Google but they utilise Imagen and Phenaki. Unfortunately, it might also mean we won't get to play with it. This looks like a really interesting tool.

Profilbild von Hungry Donk-E
Hungry Donk-Evor 1 Jahr

🥕Wow! This is awesome! I recently tried something similar here using i2v

Profilbild von MayorkingAI
MayorkingAIvor 1 Jahr

very interesting!

Profilbild von el.cine
el.cinevor 1 Jahr

👍👍

Profilbild von Ivan P.
Ivan P.vor 1 Jahr

@SmagaAlex, we should explain how @Openmagic_ai functions in a similar manner.

Profilbild von Michael Ten 🌨🎶🫐🍀
Michael Ten 🌨🎶🫐🍀vor 1 Jahr

That's pretty cool. Machine learning sure is advancing quickly

Profilbild von el.cine
el.cinevor 1 Jahr

It’s super quick mate

Profilbild von andwhynut
andwhynutvor 1 Jahr

pinta fresco este reconX, Thx for sharing!!! have u seen the new vidu?

Profilbild von Teodora P L
Teodora P Lvor 1 Jahr

Ooo wow this is going to be killer for Teal Estate

Ähnliche Videos

📢📢 𝐀𝐯𝐚𝐭𝟑𝐫 📢📢 Avat3r creates high-quality 3D head avatars from just a few input images in a single forward pass with a new dynamic 3DGS reconstruction model. Video: Project: Our core idea is to make Gaussian Reconstruction Models animatable. We find that a simple cross-attention to an expression code sequence is already sufficient to model complex facial expressions. We then incorporate position maps from DUSt3R and feature maps from Sapiens to facilitate the prediction task. While DUSt3R's position maps act as a pixel-aligned initialization for the Gaussians' positions, the Sapiens feature maps help the cross-view transformer to match corresponding image tokens in the 4 input images. One major challenge in creating a 3D head avatar from smartphone images comes from inconsistent facial expressions when the subject could not remain perfectly static during the capture. We eliminate this static requirement by simply showing our model input images with different facial expressions during training. This technique makes our model robust to inconsistent input images later on. Finally, we show that despite the model has been trained with 4 input images, one can even create a 3D head avatar when only a single image is available. To achieve this, we employ a pre-trained 3D GAN to lift the single image to 3D and then render the 4 input images for our model. This allows us to create 3D head avatars from single images and even highly out-of-distribution examples like AI generated faces, paintings or statues. Great work by Tobias Kirschstein from his internship at Meta with Javier Romero, Artem Sevastopolsky, and Shunsuke Saito

Matthias Niessner

74,698 Aufrufe • vor 1 Jahr