Rxivist logo

Rxivist combines preprints from bioRxiv with data from Twitter to help you find the papers being discussed in your field. Currently indexing 73,782 bioRxiv papers from 321,061 authors.

Deep image reconstruction from human brain activity

By Guohua Shen, Tomoyasu Horikawa, Kei Majima, Yukiyasu Kamitani

Posted 28 Dec 2017
bioRxiv DOI: 10.1101/240317 (published DOI: 10.1371/journal.pcbi.1006633)

Machine learning-based analysis of human functional magnetic resonance imaging (fMRI) patterns has enabled the visualization of perceptual content. However, it has been limited to the reconstruction with low-level image bases or to the matching to exemplars. Recent work showed that visual cortical activity can be decoded (translated) into hierarchical features of a deep neural network (DNN) for the same input image, providing a way to make use of the information from hierarchical visual features. Here, we present a novel image reconstruction method, in which the pixel values of an image are optimized to make its DNN features similar to those decoded from human brain activity at multiple layers. We found that the generated images resembled the stimulus images (both natural images and artificial shapes) and the subjective visual content during imagery. While our model was solely trained with natural images, our method successfully generalized the reconstruction to artificial shapes, indicating that our model indeed reconstructs or generates images from brain activity, not simply matches to exemplars. A natural image prior introduced by another deep neural network effectively rendered semantically meaningful details to reconstructions by constraining reconstructed images to be similar to natural images. Furthermore, human judgment of reconstructions suggests the effectiveness of combining multiple DNN layers to enhance visual quality of generated images. The results suggest that hierarchical visual information in the brain can be effectively combined to reconstruct perceptual and subjective images.

Download data

  • Downloaded 125,205 times
  • Download rankings, all-time:
    • Site-wide: 3 out of 73,782
    • In neuroscience: 1 out of 13,273
  • Year to date:
    • Site-wide: 191 out of 73,782
  • Since beginning of last month:
    • Site-wide: 191 out of 73,782

Altmetric data


Downloads over time

Distribution of downloads per paper, site-wide


PanLingua

Sign up for the Rxivist weekly newsletter! (Click here for more details.)


News