Visual image reconstruction from human brain activity using a combination of multiscale local image decoders.

By Yoichi Miyawaki, Hajime Uchida, Okito Yamashita, Masa-aki Sato, Y. Morito, Hiroki C. Tanabe, Norihiro Sadato, Yukiyasu Kamitani. Neuron, 2008

603 citations recorded by the source corpus.

Subfields: Biophysics, Cognitive Neuroscience, Electrical and Electronic Engineering

View Paper: https://www.semanticscholar.org/paper/f1c08d9d3856e0e0085bbb09f8748be44071616d

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Biophysics

In Cognitive Neuroscience

In Electrical and Electronic Engineering

Citations in the corpus

Cognitive computational neuroscience (2018, background): “A particularly impressive form of decoding is stimulus reconstruction.(87,88,89) Like ordinary decoding, reconstruction maps brain activity patterns to stimuli.”
Cerebellar supervised learning revisited: biophysical modeling and degrees-of-freedom control. (2011, methodology): “These techniques are widely utilized in estimating brain activities, brain decoding, and brain machine interfaces [74–76].”
A Primer on Pattern-Based Approaches to fMRI: Principles, Pitfalls, and Perspectives. (2015, methodology): “One field that has pioneered this approach is visual image reconstruction (Thirion et al., 2006; Miyawaki et al., 2008; Naselaris et al., 2009; Nishimoto et al., 2011; Schoenmakers et al., 2013).”
Decoding and reconstructing color from responses in human visual cortex (2009, positive): “Reconstructing stimuli directly from brain activity has also been demonstrated for binary black and white patterns (Miyawaki et al., 2008).”
Decoding brain states from fMRI connectivity graphs (2011, background): “…on a classi ﬁ er to predict the subject's brain state from the BOLD responses in a set of selected voxels, such as visual (Cox and Savoy, 2003; Haynes and Rees, 2005; Kamitani and Tong, 2005; Thirion et al., 2006; Kay et al., 2008; Miyawaki et al., 2008) or auditory cortices (Ethofer et al., 2009).”
Neural Encoding and Decoding with Deep Learning for Dynamic Natural Vision (2016, methodology): “Miyawaki et al. previously used a similar computational strategy for direct reconstruction of simple pixel patterns, for example, letters and shapes, with binary-valued local image bases ( Miyawaki et al. 2008).”
Encoding and decoding in fMRI (2010, methodology): “For example, the study of Miyawaki et al. (2008) used a linearizing decoding model to reconstruct flashing black-and-white geometrical patterns from activity measured in visual cortex.”
Reconstructing visual experiences from brain activity evoked by natural movies (2011, neutral): “Identification accuracy [7, 19] measures how well a model can correctly associate an observed BOLD signal pattern with the specific stimulus that evoked it.”
Generic decoding of seen and imagined objects using hierarchical visual features (2015, methodology): “The model enabled reconstruction of arbitrary visual images from brain activity by combining the outputs of the local decoders despite having been trained with brain activity for a small number of random images.”
High-resolution image reconstruction with latent diffusion models from human brain activity (2023, background): “Reconstructing visual images from brain activity, such as that measured by functional Magnetic Resonance Imaging (fMRI), is an intriguing but challenging problem, because the underlying representations in the brain are largely unknown, and the sample size typically associated with brain data is rela”