DREAM: Visual Decoding from Reversing Human Visual System - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2023

DREAM: Visual Decoding from Reversing Human Visual System

Abstract

In this work we present DREAM, an fMRI-to-image method for reconstructing viewed images from brain activities, grounded on fundamental knowledge of the human visual system. We craft reverse pathways that emulate the hierarchical and parallel nature of how humans perceive the visual world. These tailored pathways are specialized to decipher semantics, color, and depth cues from fMRI data, mirroring the forward pathways from visual stimuli to fMRI recordings. To do so, two components mimic the inverse processes within the human visual system: the Reverse Visual Association Cortex (R-VAC) which reverses pathways of this brain region, extracting semantics from fMRI data; the Reverse Parallel PKM (R-PKM) component simultaneously predicting color and depth from fMRI signals. The experiments indicate that our method outperforms the current state-of-the-art models in terms of the consistency of appearance, structure, and semantics. Code will be made publicly available to facilitate further research in this field.

Dates and versions

hal-04366806 , version 1 (29-12-2023)

Identifiers

Cite

Weihao Xia, Raoul de Charette, Cengiz Öztireli, Jing-Hao Xue. DREAM: Visual Decoding from Reversing Human Visual System. Winter Conference on Applications of Computer Vision (WACV), Jan 2024, Waikola, Hawaii, United States. ⟨hal-04366806⟩

Collections

INRIA INRIA2
14 View
0 Download

Altmetric

Share

Gmail Mastodon Facebook X LinkedIn More