Загрузка видео...
Не удалось загрузить видео
(1/2) 📢📢𝐃𝐢𝐟𝐟𝐮𝐬𝐢𝐨𝐧𝐀𝐯𝐚𝐭𝐚𝐫𝐬 📢📢 High-fidelity 3D head avatars with precise control over viewpoint, expression, and pose. -> Our parametric 3D model enables control & consistency + 2D diffusion makes it photoreal.
66,436 просмотров • 2 лет назад •via X (Twitter)
Комментарии: 7

(2/2) We propose a diffusion-based neural renderer that translates 3D renderings from a neural parametric head model (NPHM) into photorealistic images. Learnable neural features are encoded on the 3D model & enforce consistency. Awesome work by @TobiasKirschst1 with @SGiebenhain

🎯 Holds breath in sniper mode... 🎮 X-Air Pro's clutch features: 💨 Breathable mesh for sweaty 1v5 moments 🔫 Perfect height for that winning headshot ⚡ 5D armrests for precise aim control 😅 "Why did I solo queue" comfort mode 🎯 For those who main AWP and live dangerously! 🪑✨ Aim better: 🎪 Headshot deal: Snipe $20 off! #AndaSeat #CSGO #Valorant #ESports #Gaming

Every time I think I have a grasp on what’s possible, new ai models like this appear and just blow the lid off of my imagination.

I tried something similar

The detailed reproduction of facial expressions, etc., is very wonderful!

Cool! How do you do the scans?

@CoffeeVectors Prepare for a whole new level of catfishing 😂
