Deep image reconstruction: Visual imagery (2023)

Reconstruction of visual imagery from human brain activity measured by fMRI
Original version:
studio.youtube...
To reconstruct visual images, we first decoded (translated) measured brain activity patterns into deep neural network (DNN) features, then fed those decoded features to a reconstruction algorithm. Our reconstruction algorithm starts from a given initial image and iteratively optimizes the pixel values so that the DNN features of the current image become similar to those decoded from brain activity. We applied our algorithm to brain activity collected during mental imagery.
This version displays images reconstructed using improved methods compared to the original 2017 video.
Left: Imagined images.
Right: Reconstructed images. The iterative optimization process is shown.
References:
Shen, G, Horikawa, T, Majima, K, Kamitani, Y, Deep image reconstruction from Human Brain Activity. bioRxiv (2017); CCN (2017)
(www.biorxiv.or...)
New Codes:
github.com/Kam...