From voxels to pixels and back: Self-supervision in natural-image reconstruction from fMRI
Not on the map. Why?
Abstract (arXiv)
Reconstructing observed images from fMRI brain recordings is challenging. Unfortunately, acquiring sufficient "labeled" pairs of {Image, fMRI} (i.e., images with their corresponding fMRI responses) to span the huge space of natural images is prohibitive for many reasons. We present a novel approach which, in addition to the scarce labeled data (training pairs), allows to train fMRI-to-image reconstruction networks also on "unlabeled" data (i.e., images without fMRI recording, and fMRI recording without images). The proposed model utilizes both an Encoder network (image-to-fMRI) and a Decoder network (fMRI-to-image). Concatenating these two networks back-to-back (Encoder-Decoder & Decoder-Encoder) allows augmenting the training with both types of unlabeled data. Importantly, it allows training on the unlabeled test-fMRI data. This self-supervision adapts the reconstruction network to the new input test-data, despite its deviation from the statistics of the scarce training data.
Key facts. Cited by 67 papers in the map (data through 7 Oct 2026). First posted on arXiv 3 Jul 2019.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 3; 2022: 9; 2023: 17; 2024: 18; 2025: 13; 2026: 7.
67 papers.
Sort:
By area:
- 2022Seeing Beyond the Brain: Conditional Diffusion Model with Sparse Masked Modeling for Vision Decodingcited by 142
- 2024MindEye2: Shared-Subject Models Enable fMRI-To-Image With 1 Hour of Datacited by 105
- 2023Natural scene reconstruction from fMRI signals using generative latent diffusioncited by 97
- 2022Mind Reader: Reconstructing complex images from brain activitiescited by 85
- 2023Cinematic Mindscapes: High-quality Video Reconstruction from Brain Activitycited by 69
- 2024MindBridge: A Cross-Subject Brain Decoding Frameworkcited by 65
- 2022Reconstruction of Perceived Images from fMRI Patterns and Semantic Brain Exploration using Instance-Conditioned GANscited by 55
- 2022Decoding natural image stimuli from fMRI data with a surface-based convolutional networkcited by 48
- 2023MindDiffuser: Controlled Image Reconstruction from Human Brain Activity with Semantic and Structural Diffusioncited by 47
- 2023UniBrain: Unify Image Reconstruction and Captioning All in One Diffusion Model from Human Brain Activitycited by 42
- 2023BrainCLIP: Bridging Brain and Visual-Linguistic Representation Via CLIP for Generic Natural Visual Stimulus Decodingcited by 36
- 2023BrainVis: Exploring the Bridge between Brain and Visual Signals via Image Reconstructioncited by 30
38 more
- 2023Controllable Mind Visual Diffusion Modelcited by 29
- 2025Bridging the Vision-Brain Gap with an Uncertainty-Aware Blur Priorcited by 28
- 2023AI-Generated Content (AIGC) for Various Data Modalities: A Surveycited by 25
- 2024Neuro-3D: Towards 3D Visual Decoding from EEG Signalscited by 23
- 2024Psychometry: An Omnifit Model for Image Reconstruction from Human Brain Activitycited by 22
- 2023Deep Neural Networks and Brain Alignment: Brain Encoding and Decoding (Survey)cited by 20
- 2022A Penny for Your (visual) Thoughts: Self-Supervised Reconstruction of Natural Movies from Brain Activitycited by 19
- 2023Seeing through the Brain: Image Reconstruction of Visual Perception from Human Brain Signalscited by 16
- 2023fMRI-PTE: A Large-scale fMRI Pretrained Transformer Encoder for Multi-Subject Brain Activity Decodingcited by 16
- 2023Brain-Conditional Multimodal Synthesis: A Survey and Taxonomycited by 15
- 2024The Wisdom of a Crowd of Brains: A Universal Brain Encodercited by 15
- 2022Visio-Linguistic Brain Encodingcited by 13
- 2024NeuroCine: Decoding Vivid Video Sequences from Human Brain Activtiescited by 10
- 2024Animate Your Thoughts: Decoupled Reconstruction of Dynamic Natural Vision from Slow Brain Activitycited by 10
- 2025BrainGuard: Privacy-Preserving Multisubject Image Reconstructions from Brain Activitiescited by 10
- 2021Natural Image Reconstruction from fMRI using Deep Learning: A Surveycited by 9
- 2023Joint fMRI Decoding and Encoding with Latent Embedding Alignmentcited by 8
- 2024Quantum-Brain: Quantum-Inspired Neural Network Approach to Vision-Brain Understandingcited by 7
- 2023MindGPT: Interpreting What You See with Non-invasive Brain Recordingscited by 6
- 2024Decoding Visual Experience and Mapping Semantics through Whole-Brain Analysis Using fMRI Foundation Modelscited by 6
- 2025A Survey of fMRI to Image Reconstructioncited by 6
- 2025A Survey on fMRI-based Brain Decoding for Reconstructing Multimodal Stimulicited by 6
- 2021More Than Meets the Eye: Self-Supervised Depth Reconstruction From Brain Activitycited by 5
- 2021Neural Photofit: Gaze-based Mental Image Reconstructioncited by 5
- 2024See Through Their Minds: Learning Transferable Neural Representation from Cross-Subject fMRIcited by 5
- 2024MindFormer: Semantic Alignment of Multi-Subject fMRI for Brain Decodingcited by 4
- 2025Brain-IT: Image Reconstruction from fMRI via Brain-Interaction Transformercited by 4
- 2022Multi-view Multi-label Fine-grained Emotion Decoding from Human Brain Activitycited by 3
- 2023DreamCatcher: Revealing the Language of the Brain with fMRI using GPT Embeddingcited by 3
- 2024BrainChat: Decoding Semantic Information from fMRI using Vision-language Pretrained Modelscited by 3
- 2025fMRI2GES: Co-speech Gesture Reconstruction from fMRI Signal with Dual Brain Decoding Alignmentcited by 3
- 2024MindSemantix: Deciphering Brain Visual Experiences with a Brain-Language Modelcited by 2
- 2025Efficient Multi Subject Visual Reconstruction from fMRI Using Aligned Representationscited by 2
- 2025From Flat to Round: Redefining Brain Decoding with Surface-Based fMRI and Cortex Structurecited by 2
- 2022Cross-view Brain Decodingcited by 1
- 2022Multiscale Voxel Based Decoding For Enhanced Natural Image Reconstruction From Brain Activitycited by 1
- 2024Deep Learning for Visual Neuroprosthesiscited by 1
- 2024Scaling up ridge regression for brain encoding in a massive individual fMRI datasetcited by 1
50 most cited of 67 All 67 (JSON)
- 2026Mind2Cloud: EEG-to-Point Cloud Generation with Two-Granularity Diffusion Decoding12 Sep 2026
- 2026Brain-IT-VQA: From Brain Signals to Answers28 May 2026
- 2026Neural Visual Decoding via Cognitive guided Adaptive Blurring and Information Constrained Alignment14 May 2026
- 2026StableMind: Source-Free Cross-Subject fMRI Decoding with Regularized Adaptation4 May 2026
- 2026NeuroFlow: Toward Unified Visual Encoding and Decoding from Neural Activity10 Apr 2026
- 2026We Should Separate Memorization from Copyright9 Feb 2026
- 2026SpikeVAEDiff: Neural Spike-based Natural Visual Scene Reconstruction via VD-VAE and Versatile Diffusion14 Jan 2026
- 2025fMRI2GES: Co-speech Gesture Reconstruction from fMRI Signal with Dual Brain Decoding Alignment1 Dec 2025
- 2025Brain-IT: Image Reconstruction from fMRI via Brain-Interaction Transformer29 Oct 2025
- 2025Beyond Grid-Locked Voxels: Neural Response Functions for Continuous Brain Encoding7 Oct 2025
- 2025HAVIR: HierArchical Vision to Image Reconstruction using CLIP-Guided Versatile Diffusion3 Oct 2025
- 2025BRAIN: Bias-Mitigation Continual Learning Approach to Vision-Brain Understanding25 Aug 2025
38 more
- 2025From Flat to Round: Redefining Brain Decoding with Surface-Based fMRI and Cortex Structure22 Jul 2025
- 2025Deep Neural Encoder-Decoder Model to Relate fMRI Brain Activity with Naturalistic Stimuli16 Jul 2025
- 2025HAVIR: HierArchical Vision to Image Reconstruction using CLIP-Guided Versatile Diffusion6 Jun 2025
- 2025Efficient Multi Subject Visual Reconstruction from fMRI Using Aligned Representations3 May 2025
- 2025A Survey on fMRI-based Brain Decoding for Reconstructing Multimodal Stimuli20 Mar 2025
- 2025Bridging the Vision-Brain Gap with an Uncertainty-Aware Blur Prior6 Mar 2025
- 2025A Survey of fMRI to Image Reconstruction24 Feb 2025
- 2025BrainGuard: Privacy-Preserving Multisubject Image Reconstructions from Brain Activities24 Jan 2025
- 2024HAIFAI: Human-AI Interaction for Mental Face Reconstruction9 Dec 2024
- 2024Quantum-Brain: Quantum-Inspired Neural Network Approach to Vision-Brain Understanding20 Nov 2024
- 2024Neuro-3D: Towards 3D Visual Decoding from EEG Signals19 Nov 2024
- 2024Decoding Visual Experience and Mapping Semantics through Whole-Brain Analysis Using fMRI Foundation Models11 Nov 2024
- 2024Training Compute-Optimal Vision Transformers for Brain Encoding17 Oct 2024
- 2024The Wisdom of a Crowd of Brains: A Universal Brain Encoder18 Jun 2024
- 2024BrainChat: Decoding Semantic Information from fMRI using Vision-language Pretrained Models10 Jun 2024
- 2024MindSemantix: Deciphering Brain Visual Experiences with a Brain-Language Model29 May 2024
- 2024MindFormer: Semantic Alignment of Multi-Subject fMRI for Brain Decoding28 May 2024
- 2024Brain3D: Generating 3D Objects from fMRI24 May 2024
- 2024Animate Your Thoughts: Decoupled Reconstruction of Dynamic Natural Vision from Slow Brain Activity6 May 2024
- 2024MindBridge: A Cross-Subject Brain Decoding Framework11 Apr 2024
- 2024Psychometry: An Omnifit Model for Image Reconstruction from Human Brain Activity29 Mar 2024
- 2024Scaling up ridge regression for brain encoding in a massive individual fMRI dataset28 Mar 2024
- 2024MindEye2: Shared-Subject Models Enable fMRI-To-Image With 1 Hour of Data17 Mar 2024
- 2024See Through Their Minds: Learning Transferable Neural Representation from Cross-Subject fMRI11 Mar 2024
- 2024NeuroCine: Decoding Vivid Video Sequences from Human Brain Activties2 Feb 2024
- 2024Deep Learning for Visual Neuroprosthesis8 Jan 2024
- 2023Brain-Conditional Multimodal Synthesis: A Survey and Taxonomy31 Dec 2023
- 2023BrainVis: Exploring the Bridge between Brain and Visual Signals via Image Reconstruction22 Dec 2023
- 2023Double-Flow GAN model for the reconstruction of perceived faces from brain activities12 Dec 2023
- 2023fMRI-PTE: A Large-scale fMRI Pretrained Transformer Encoder for Multi-Subject Brain Activity Decoding1 Nov 2023
- 2023MindGPT: Interpreting What You See with Non-invasive Brain Recordings27 Sep 2023
- 2023AI-Generated Content (AIGC) for Various Data Modalities: A Survey27 Aug 2023
- 2023UniBrain: Unify Image Reconstruction and Captioning All in One Diffusion Model from Human Brain Activity14 Aug 2023
- 2023MindDiffuser: Controlled Image Reconstruction from Human Brain Activity with Semantic and Structural Diffusion8 Aug 2023
- 2023Seeing through the Brain: Image Reconstruction of Visual Perception from Human Brain Signals27 Jul 2023
- 2023Deep Neural Networks and Brain Alignment: Brain Encoding and Decoding (Survey)17 Jul 2023
- 2023DreamCatcher: Revealing the Language of the Brain with fMRI using GPT Embedding16 Jun 2023
- 2023Cinematic Mindscapes: High-quality Video Reconstruction from Brain Activity19 May 2023
50 newest of 67 All 67 (JSON)
- 2022Seeing Beyond the Brain: Conditional Diffusion Model with Sparse Masked Modeling for Vision Decodingcited by 142
- 2023Natural scene reconstruction from fMRI signals using generative latent diffusioncited by 97
- 2023UniBrain: Unify Image Reconstruction and Captioning All in One Diffusion Model from Human Brain Activitycited by 42
- 2023Controllable Mind Visual Diffusion Modelcited by 29
- 2025Brain-IT: Image Reconstruction from fMRI via Brain-Interaction Transformercited by 4
- 2025HAVIR: HierArchical Vision to Image Reconstruction using CLIP-Guided Versatile Diffusioncited by 1
- 2023MindDiffuser: Controlled Image Reconstruction from Human Brain Activity with Semantic and Structural Diffusioncited by 0
- 2025Brain-IT: Image Reconstruction from fMRI via Brain-Interaction Transformer29 Oct 2025
- 2025HAVIR: HierArchical Vision to Image Reconstruction using CLIP-Guided Versatile Diffusion3 Oct 2025
- 2023UniBrain: Unify Image Reconstruction and Captioning All in One Diffusion Model from Human Brain Activity14 Aug 2023
- 2023Controllable Mind Visual Diffusion Model17 May 2023
- 2023MindDiffuser: Controlled Image Reconstruction from Human Brain Activity with Semantic and Structural Diffusion24 Mar 2023
- 2023Natural scene reconstruction from fMRI signals using generative latent diffusion9 Mar 2023
- 2022Seeing Beyond the Brain: Conditional Diffusion Model with Sparse Masked Modeling for Vision Decoding13 Nov 2022
- 2024MindEye2: Shared-Subject Models Enable fMRI-To-Image With 1 Hour of Datacited by 105
- 2022Mind Reader: Reconstructing complex images from brain activitiescited by 85
- 2023Cinematic Mindscapes: High-quality Video Reconstruction from Brain Activitycited by 69
- 2024MindBridge: A Cross-Subject Brain Decoding Frameworkcited by 65
- 2022Reconstruction of Perceived Images from fMRI Patterns and Semantic Brain Exploration using Instance-Conditioned GANscited by 55
- 2022Decoding natural image stimuli from fMRI data with a surface-based convolutional networkcited by 48
- 2023MindDiffuser: Controlled Image Reconstruction from Human Brain Activity with Semantic and Structural Diffusioncited by 47
- 2023BrainCLIP: Bridging Brain and Visual-Linguistic Representation Via CLIP for Generic Natural Visual Stimulus Decodingcited by 36
- 2023BrainVis: Exploring the Bridge between Brain and Visual Signals via Image Reconstructioncited by 30
- 2025Bridging the Vision-Brain Gap with an Uncertainty-Aware Blur Priorcited by 28
- 2023AI-Generated Content (AIGC) for Various Data Modalities: A Surveycited by 25
- 2024Neuro-3D: Towards 3D Visual Decoding from EEG Signalscited by 23
12 most cited of 58 All 58 (JSON)
- 2026Mind2Cloud: EEG-to-Point Cloud Generation with Two-Granularity Diffusion Decoding12 Sep 2026
- 2026Brain-IT-VQA: From Brain Signals to Answers28 May 2026
- 2026Neural Visual Decoding via Cognitive guided Adaptive Blurring and Information Constrained Alignment14 May 2026
- 2026StableMind: Source-Free Cross-Subject fMRI Decoding with Regularized Adaptation4 May 2026
- 2026NeuroFlow: Toward Unified Visual Encoding and Decoding from Neural Activity10 Apr 2026
- 2026We Should Separate Memorization from Copyright9 Feb 2026
- 2026SpikeVAEDiff: Neural Spike-based Natural Visual Scene Reconstruction via VD-VAE and Versatile Diffusion14 Jan 2026
- 2025fMRI2GES: Co-speech Gesture Reconstruction from fMRI Signal with Dual Brain Decoding Alignment1 Dec 2025
- 2025Beyond Grid-Locked Voxels: Neural Response Functions for Continuous Brain Encoding7 Oct 2025
- 2025BRAIN: Bias-Mitigation Continual Learning Approach to Vision-Brain Understanding25 Aug 2025
- 2025From Flat to Round: Redefining Brain Decoding with Surface-Based fMRI and Cortex Structure22 Jul 2025
- 2025Deep Neural Encoder-Decoder Model to Relate fMRI Brain Activity with Naturalistic Stimuli16 Jul 2025
12 newest of 58 All 58 (JSON)