DailyNews
vip

According to news from IT House on June 28, researchers from the Max Planck Institute of Computer Science, MIT CSAIL and Google have recently studied a new method of controlling GAN called DragGAN, just click and drag to quickly adjust the subject of the photo position, posture, expression, size and angle, etc. The project is currently open source on GitHub. The researchers say their method outperforms SOTA in GAN-based operations and opens new directions for image editing. In the coming months, they hope to extend point-based editing to 3D generative models.

View Original
This page may contain third-party content, which is provided for information purposes only (not representations/warranties) and should not be considered as an endorsement of its views by Gate, nor as financial or professional advice. See Disclaimer for details.
  • Reward
  • Comment
  • Share
Comment
0/400
No comments
Trade Crypto Anywhere Anytime
qrCode
Scan to download Gate app
Community
English
  • 简体中文
  • English
  • Tiếng Việt
  • 繁體中文
  • Español
  • Русский
  • Français (Afrique)
  • Português (Portugal)
  • Bahasa Indonesia
  • 日本語
  • بالعربية
  • Українська
  • Português (Brasil)