Photorealistic Reconstruction of Visual Texture From EEG Signals

Recent advances in brain decoding have made it possible to classify image categories based on neural activity. Increasing numbers of studies have further attempted to reconstruct the image itself. However, because images of objects and scenes inherently involve spatial layout information, the recons...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Suguru Wakita, Taiki Orima, Isamu Motoyoshi
Formato:	article
Lenguaje:	EN
Publicado:	Frontiers Media S.A. 2021
Materias:	visual texture multimodal variational auto encoder (MVAE) DNN (deep neural network) brain decoding EEG Neurosciences. Biological psychiatry. Neuropsychiatry RC321-571
Acceso en línea:	https://doaj.org/article/cd3a66ddb018435eb3ee5c3adcf9c289
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:cd3a66ddb018435eb3ee5c3adcf9c289
record_format	dspace
spelling	oai:doaj.org-article:cd3a66ddb018435eb3ee5c3adcf9c2892021-11-19T07:47:51ZPhotorealistic Reconstruction of Visual Texture From EEG Signals1662-518810.3389/fncom.2021.754587https://doaj.org/article/cd3a66ddb018435eb3ee5c3adcf9c2892021-11-01T00:00:00Zhttps://www.frontiersin.org/articles/10.3389/fncom.2021.754587/fullhttps://doaj.org/toc/1662-5188Recent advances in brain decoding have made it possible to classify image categories based on neural activity. Increasing numbers of studies have further attempted to reconstruct the image itself. However, because images of objects and scenes inherently involve spatial layout information, the reconstruction usually requires retinotopically organized neural data with high spatial resolution, such as fMRI signals. In contrast, spatial layout does not matter in the perception of “texture,” which is known to be represented as spatially global image statistics in the visual cortex. This property of “texture” enables us to reconstruct the perceived image from EEG signals, which have a low spatial resolution. Here, we propose an MVAE-based approach for reconstructing texture images from visual evoked potentials measured from observers viewing natural textures such as the textures of various surfaces and object ensembles. This approach allowed us to reconstruct images that perceptually resemble the original textures with a photographic appearance. The present approach can be used as a method for decoding the highly detailed “impression” of sensory stimuli from brain activity.Suguru WakitaTaiki OrimaTaiki OrimaIsamu MotoyoshiFrontiers Media S.A.articlevisual texturemultimodal variational auto encoder (MVAE)DNN (deep neural network)brain decodingEEGNeurosciences. Biological psychiatry. NeuropsychiatryRC321-571ENFrontiers in Computational Neuroscience, Vol 15 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	visual texture multimodal variational auto encoder (MVAE) DNN (deep neural network) brain decoding EEG Neurosciences. Biological psychiatry. Neuropsychiatry RC321-571
spellingShingle	visual texture multimodal variational auto encoder (MVAE) DNN (deep neural network) brain decoding EEG Neurosciences. Biological psychiatry. Neuropsychiatry RC321-571 Suguru Wakita Taiki Orima Taiki Orima Isamu Motoyoshi Photorealistic Reconstruction of Visual Texture From EEG Signals
description	Recent advances in brain decoding have made it possible to classify image categories based on neural activity. Increasing numbers of studies have further attempted to reconstruct the image itself. However, because images of objects and scenes inherently involve spatial layout information, the reconstruction usually requires retinotopically organized neural data with high spatial resolution, such as fMRI signals. In contrast, spatial layout does not matter in the perception of “texture,” which is known to be represented as spatially global image statistics in the visual cortex. This property of “texture” enables us to reconstruct the perceived image from EEG signals, which have a low spatial resolution. Here, we propose an MVAE-based approach for reconstructing texture images from visual evoked potentials measured from observers viewing natural textures such as the textures of various surfaces and object ensembles. This approach allowed us to reconstruct images that perceptually resemble the original textures with a photographic appearance. The present approach can be used as a method for decoding the highly detailed “impression” of sensory stimuli from brain activity.
format	article
author	Suguru Wakita Taiki Orima Taiki Orima Isamu Motoyoshi
author_facet	Suguru Wakita Taiki Orima Taiki Orima Isamu Motoyoshi
author_sort	Suguru Wakita
title	Photorealistic Reconstruction of Visual Texture From EEG Signals
title_short	Photorealistic Reconstruction of Visual Texture From EEG Signals
title_full	Photorealistic Reconstruction of Visual Texture From EEG Signals
title_fullStr	Photorealistic Reconstruction of Visual Texture From EEG Signals
title_full_unstemmed	Photorealistic Reconstruction of Visual Texture From EEG Signals
title_sort	photorealistic reconstruction of visual texture from eeg signals
publisher	Frontiers Media S.A.
publishDate	2021
url	https://doaj.org/article/cd3a66ddb018435eb3ee5c3adcf9c289
work_keys_str_mv	AT suguruwakita photorealisticreconstructionofvisualtexturefromeegsignals AT taikiorima photorealisticreconstructionofvisualtexturefromeegsignals AT taikiorima photorealisticreconstructionofvisualtexturefromeegsignals AT isamumotoyoshi photorealisticreconstructionofvisualtexturefromeegsignals
_version_	1718420287019548672

Photorealistic Reconstruction of Visual Texture From EEG Signals

Ejemplares similares