Fine-grained image generation with EEG multi-level semantics.

Journal: Computer methods and programs in biomedicine
Published Date: Jun 22, 2025

Abstract

BACKGROUND AND OBJECTIVE: Decoding visual information from electroencephalography (EEG) signals is crucial in neuroscience and artificial intelligence. While existing methods have been able to extract high-level features such as object categories, the capability of extracting fine-grained attributes, such as color distribution, remains insufficient. In this work, we propose EEG2IM, a novel framework that integrates multi-level EEG semantic features to guide a diffusion model for fine-grained image generation.

Authors

  • Wenjie Cheng
    School of Computer Science and Technology, Hangzhou Dianzi University, Hangzhou, Zhejiang, China.
  • Jun Tan
    School of Mathematics, Sun Yat-Sen University, Guangzhou, Guangdong, China.
  • Lizhi Wang
    School of Industrial Engineering and Management, Oklahoma State University, Stillwater, OK, United States.
  • María Trinidad Herrero
    Clinical and Experimental Neuroscience (NiCE), Institute for Aging Research, Biomedical Institute for Bio-Health Research of Murcia (IMIB-Arrixaca), School of Medicine, University of Murcia, Campus Mare Nostrum, 30120 Murcia, Spain.
  • Hong Zeng
    School of Computer Science and Technology, Hangzhou Dianzi University, China.

Keywords

External Resources

Popular Topics
Recent Journals