Mental DailyMental Daily
  • Clinical
  • Health
  • I/O
  • Cybernetic
  • Social
  • More
    • Opinion
    • My Bookmarks
Aa
Mental Daily
Aa
  • Clinical
  • Health
  • I/O
  • Cybernetic
  • Social
  • Opinion
Search
  • Clinical
  • Health
  • I/O
  • Cybernetic
  • Social
  • More
    • Opinion
    • My Bookmarks
Follow US
  • Twitter
  • Facebook
  • Instagram
  • Inc. Profile
  • Google Play Store
© 2022 - Mental Daily. All Rights Reserved.
Clinical

Researchers use AI to generate video from brain activity

Staff Writer
Staff Writer 2 weeks ago
Updated 2023/05/25 at 10:43 PM
Share
SHARE

The process for creating video from brain scans was recently reported by experts from the National University of Singapore and the Chinese University of Hong Kong. There is a copy of the study available on the public arXiv preprint server.

To create high-quality videos with little to no jerkiness, researchers Jiaxin Qing, Zijiao Chen, and Juan Helen Zhou used a technique called functional magnetic resonance imaging (fMRI) and coupled data retrieved through imaging with the deep learning model Stable Diffusion.

Commonly used for image generation, AI-assisted Stable Diffusion has been reported to successfully recreate still imagery gleaned from brain activity in recent months. However, as reported by Qing and company, the challenge of retrieving continuous visual images is significant.

fMRI typically uses blood oxygenation level-dependent (BOLD) signals to take pictures of brain activity every few seconds. Because of this, the video quality would suffer. There are 30 frames per second as the norm for video recording.

“We show that high-quality videos of arbitrary frame rates can be reconstructed with Mind-Video using adversarial guidance. The recovered videos were evaluated with various semantic and pixel-level metrics,” the study’s authors explained in their report.

“We achieved an average accuracy of 85% in semantic classification tasks and 0.19 in structural similarity index (SSIM), outperforming the previous state-of-the-art by 45%. We also show that our model is biologically plausible and interpretable, reflecting established physiological processes.”

You Might Also Like

Study suggests semaglutide may reduce alcohol intake and relapse-like drinking

Cognitive disorders may develop due to molecular overreaction to ribosome stalling

Researchers have uncovered hints as to why immune cells appear to cause brain damage

People are more creative upon awakening from the earliest stage of sleep: new study

Memory loss associated with Alzheimer’s may be mitigated through deep sleep

TAGGED: AI, artificial intelligence, brain imaging
Staff Writer May 25, 2023
Share this Article
Facebook Twitter Whatsapp Whatsapp Email Print
Previous Article New research emphasizes the need for neuroscientific evidence in rape trials
Next Article New study examines how papal supremacy shapes ideal societies

Recommended

Clinical

Study suggests semaglutide may reduce alcohol intake and relapse-like drinking

3 Min Read
Clinical

Cognitive disorders may develop due to molecular overreaction to ribosome stalling

2 Min Read
Clinical

Researchers have uncovered hints as to why immune cells appear to cause brain damage

1 Min Read
Clinical

People are more creative upon awakening from the earliest stage of sleep: new study

1 Min Read
//

We are a trusted online source for research news and resources on all aspects of the mind and human behavior.

Verticals

  • Clinical
  • Health
  • Social
  • I/O
  • Opinion

Social

  • Twitter
  • Facebook
  • Instagram
  • Inc. Profile
  • Google Play Store

Links

  • About
  • Contact
  • The Editor
  • Terms & Conditions
  • Privacy Policy
Follow US

© 2022 Mental Daily. All Rights Reserved.

  • Twitter
  • Facebook
  • Instagram
  • Inc. Profile
  • Google Play Store

Removed from reading list

Undo
Welcome Back!

Sign in to your account

Lost your password?