mlsanityData to 14 Oct 2026

Natural Image Reconstruction from fMRI using Deep Learning: A Survey

arXiv 2110.09006 ↗First posted 18 Oct 2021cs.CV q-bio.NC stat.MLcited by 9

Not on the map. Why?

Abstract (arXiv)

With the advent of brain imaging techniques and machine learning tools, much effort has been devoted to building computational models to capture the encoding of visual information in the human brain. One of the most challenging brain decoding tasks is the accurate reconstruction of the perceived natural images from brain activities measured by functional magnetic resonance imaging (fMRI). In this work, we survey the most recent deep learning methods for natural image reconstruction from fMRI. We examine these methods in terms of architectural design, benchmark datasets, and evaluation metrics and present a fair performance evaluation across standardized evaluation metrics. Finally, we discuss the strengths and limitations of existing studies and present potential future directions.

Key facts. Cited by 9 papers in the map (data through 14 Oct 2026). Builds on 26 of its 84 references that are in the map. First posted on arXiv 18 Oct 2021.

Builds on

26 of 84 references.

References · 26

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  3. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  4. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  5. 2015Distilling the Knowledge in a Neural Networkcited by 10,324
  6. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,475
  7. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,527
  8. 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,057
  9. 2013Auto-Encoding Variational Bayescited by 4,053
  10. 2014Deep Learning Face Attributes in the Wildcited by 3,693
  11. 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,054
  12. 2016Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoisingcited by 1,358
14 more
  1. 2020Image Segmentation Using Deep Learning: A Surveycited by 660
  2. 2014Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFscited by 554
  3. 2015Autoencoding beyond pixels using a learned similarity metriccited by 407
  4. 2014Understanding Deep Image Representations by Inverting Themcited by 403
  5. 2017A Downsampled Variant of ImageNet as an Alternative to the CIFAR datasetscited by 377
  6. 2016Efficient Multi-Scale 3D CNN with Fully Connected CRF for Accurate Brain Lesion Segmentationcited by 263
  7. 2019Large Scale Adversarial Representation Learningcited by 239
  8. 2015Inverting Visual Representations with Convolutional Networkscited by 170
  9. 2015Generic decoding of seen and imagined objects using hierarchical visual featurescited by 120
  10. 2019From voxels to pixels and back: Self-supervision in natural-image reconstruction from fMRIcited by 67
  11. 2020Reconstructing Natural Scenes from fMRI Patterns using BigBiGANcited by 44
  12. 2018Reconstructing Faces from fMRI Patterns using Deep Generative Neural Networkscited by 43
  13. 2021Reconstructing Perceptive Images from Brain Activity by Shape-Semantic GANcited by 32
  14. 2020BigGAN-based Bayesian reconstruction of natural images from human brain activitycited by 10

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 1; 2023: 3; 2024: 2; 2025: 2; 2026: 1.

9 papers.

  1. 2022Mind Reader: Reconstructing complex images from brain activitiescited by 85
  2. 2023MindDiffuser: Controlled Image Reconstruction from Human Brain Activity with Semantic and Structural Diffusioncited by 47
  3. 2024Psychometry: An Omnifit Model for Image Reconstruction from Human Brain Activitycited by 22
  4. 2025ViEEG: Hierarchical Visual Neural Representation for EEG Brain Decodingcited by 5
  5. 2025SYNAPSE: Synergizing an Adapter and Finetuning for High-Fidelity EEG Synthesis from a CLIP-Aligned Encodercited by 1
  6. 2023MindDiffuser: Controlled Image Reconstruction from Human Brain Activity with Semantic and Structural Diffusioncited by 0
  7. 2023On Functional Activations in Deep Neural Networkscited by 0
  8. 2024Optimized two-stage AI-based Neural Decoding for Enhanced Visual Stimulus Reconstruction from fMRI Datacited by 0
  9. 2026Lost in Visual Translation: A VLM-Assisted Perceptual-Semantic Coherence Framework for EEG-to-Image Reconstructioncited by 0