mlsanityData to 14 Oct 2026

From Flat to Round: Redefining Brain Decoding with Surface-Based fMRI and Cortex Structure

arXiv 2507.16389 ↗First posted 22 Jul 2025cs.CV cs.AIcited by 2

Not on the map. Why?

Abstract (arXiv)

Reconstructing visual stimuli from human brain activity (e.g., fMRI) bridges neuroscience and computer vision by decoding neural representations. However, existing methods often overlook critical brain structure-function relationships, flattening spatial information and neglecting individual anatomical variations. To address these issues, we propose (1) a novel sphere tokenizer that explicitly models fMRI signals as spatially coherent 2D spherical data on the cortical surface; (2) integration of structural MRI (sMRI) data, enabling personalized encoding of individual anatomical variations; and (3) a positive-sample mixup strategy for efficiently leveraging multiple fMRI scans associated with the same visual stimulus. Collectively, these innovations enhance reconstruction accuracy, biological interpretability, and generalizability across individuals. Experiments demonstrate superior reconstruction performance compared to SOTA methods, highlighting the effectiveness and interpretability of our biologically informed approach.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 33 of its 53 references that are in the map. First posted on arXiv 22 Jul 2025.

Builds on

33 of 53 references.

References · 33

  1. 2017Attention Is All You Needcited by 60,361
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  3. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  4. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  5. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  6. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,255
  7. 2018Representation Learning with Contrastive Predictive Codingcited by 7,777
  8. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,733
  9. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,442
  10. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,475
  11. 2020Unsupervised Learning of Visual Features by Contrasting Cluster Assignmentscited by 2,857
  12. 2022Versatile Diffusion: Text, Images and Variations All in One Diffusion Modelcited by 199
21 more
  1. 2023Reconstructing the Mind's Eye: fMRI-to-Image with Contrastive Learning and Diffusion Priorscited by 160
  2. 2022Seeing Beyond the Brain: Conditional Diffusion Model with Sparse Masked Modeling for Vision Decodingcited by 144
  3. 2015Generic decoding of seen and imagined objects using hierarchical visual featurescited by 120
  4. 2023Natural scene reconstruction from fMRI signals using generative latent diffusioncited by 97
  5. 2019Spherical CNNs on Unstructured Gridscited by 79
  6. 2023Cinematic Mindscapes: High-quality Video Reconstruction from Brain Activitycited by 71
  7. 2019From voxels to pixels and back: Self-supervision in natural-image reconstruction from fMRIcited by 67
  8. 2024MindBridge: A Cross-Subject Brain Decoding Frameworkcited by 66
  9. 2022Decoding Visual Neural Representations by Multimodal Learning of Brain-Visual-Linguistic Featurescited by 63
  10. 2022Reconstruction of Perceived Images from fMRI Patterns and Semantic Brain Exploration using Instance-Conditioned GANscited by 55
  11. 2022Decoding natural image stimuli from fMRI data with a surface-based convolutional networkcited by 49
  12. 2023DREAM: Visual Decoding from Reversing Human Visual Systemcited by 44
  13. 2023Contrast, Attend and Diffuse to Decode High-Resolution Images from Brain Activitiescited by 36
  14. 2019Spherical U-Net on Cortical Surfaces: Methods and Applicationscited by 34
  15. 2024NeuroPictor: Refining fMRI-to-Image Reconstruction via Multi-individual Pretraining and Multi-level Modulationcited by 34
  16. 2024UMBRAE: Unified Multimodal Brain Decodingcited by 32
  17. 2024Psychometry: An Omnifit Model for Image Reconstruction from Human Brain Activitycited by 22
  18. 2024A Closer Look at GAN Priors: Exploiting Intermediate Features for Enhanced Model Inversion Attackscited by 18
  19. 2024Neuro-Vision to Language: Enhancing Brain Recording-based Visual Reconstruction and Language Interactioncited by 16
  20. 2023Joint fMRI Decoding and Encoding with Latent Embedding Alignmentcited by 8
  21. 2025ICAS: Detecting Training Data from Autoregressive Image Generative Modelscited by 6

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 1.

2 papers.

  1. 2025Scaling Vision Transformers for Functional MRI with Flat Mapscited by 5
  2. 2026NeurIPS: Neuro-anatomical Inductive Priors for Sphere-based Brain Decodingcited by 0