Загрузка видео...

Не удалось загрузить видео

На главную

All these isometric buildings were generated with AI - from a single input image each (examples below 👇) Just a few minutes per 3D mesh (no textures yet). This is #Sparc3D, a new generative 3D model announced just a few days ago. 🧵

16,012 просмотров • 1 год назад •via X (Twitter)

Комментарии: 8

Фото профиля Emm | scenario.com
Emm | scenario.com1 год назад

This glb was all 100% generated. From one single image. Unreal.

Фото профиля Emm | scenario.com
Emm | scenario.com1 год назад

Sparc3D is a project by @zhhol141234, Math Magic, and Nanyang Technological University (Singapore 🇸🇬) "Sparse Representation and Construction for High-Resolution 3D Shapes Modeling" Read more at (+ demo available)

Фото профиля Emm | scenario.com
Emm | scenario.com1 год назад

Here's the Sagrada Familia in Barcelona

Фото профиля Mobile Scanner
Mobile Scanner1 год назад

Scan any documents, convert images into text, PDF files, etc. 👍

Фото профиля Michael + puppetto.com
Michael + puppetto.com1 год назад

Ooooh these look tasty

Фото профиля Nanya⭐️
Nanya⭐️1 год назад

I am impressed

Фото профиля Heba AI
Heba AI1 год назад

Better than Hunyuan? It has some problems figuring out whats on the other side of the isometric object. Also the edges have unwanted bewels too often.

Фото профиля Emm | scenario.com
Emm | scenario.com1 год назад

Much more precise than Hunyuan though, in a lot of cases

Похожие видео

📢📢 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 просмотров • 1 год назад