正在加载视频...

视频加载失败

Finally! #PHORHUM -- our 3D human reconstruction model from a single image -- is available to the research community 🎉 PHORHUM is joint work with Mihai Zanfir & Cristian Sminchisescu. How to get access: 👇

12,764 次观看 • 3 年前 •via X (Twitter)

4 条评论

Thiemo Alldieck 的头像
Thiemo Alldieck3 年前

1. Go to 2. Request access 3. We will get back to you shortly If you or your group already has access to the "Google 3D Human Models" repository, you should already have access by now or will be given access in the next days! Questions? DMs are open!

Babusi Nyoni 的头像
Babusi Nyoni3 年前

@MihaiZanfir5 @CSminchisescu I waited so long for this you have no idea 🎉

Mohamed Abdelhamid 👨‍💻 的头像
Mohamed Abdelhamid 👨‍💻3 年前

@MihaiZanfir5 @CSminchisescu 😆Amazing, I wish I have participated In that project, I proposed this idea for the graduation project 4 months ago, but unfortunately, our professors were not experienced enough and rejected this idea.and others It was the same but I wanted to apply it on yu-gi-yo monster card .

Mohamed Abdo 的头像
Mohamed Abdo3 年前

@MihaiZanfir5 @CSminchisescu Great job, congrats,

相关视频

📢📢 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

74,687 次观看 • 1 年前