- Here we have collect info about all the works that may be useful for writing our paper
- We divide these works by topic in order to structure them
- Each of the contributors is responsible for their part of the work, as specified in the table
Note
This review table will be updated, so it is not a final version
Topic | Title | Year | Authors | Paper | Code | Summary |
---|---|---|---|---|---|---|
Datasets with simultaneous fMRI-EEG signals @kisnikser |
An open-access dataset of naturalistic viewing using simultaneous EEG-fMRI | 2023 | Qawi K. Telesford et al. | scientific data | GitHub | TODO |
Open multimodal iEEG-fMRI dataset from naturalistic stimulation with a short audiovisual film | 2022 | Julia Berezutskaya et al. | scientific data | GitHub #1, GitHub #2 | ||
Simultaneous EEG and functional MRI data during rest and sleep from humans | 2023 | Yameng Gu et al. | Data in Brief | Download | ||
Simultaneous and independent electroencephalography and magnetic resonance imaging: A multimodal neuroimaging dataset | 2023 | Jonathan Gallego-Rudolf et al. | Data in Brief | Download | ||
Methods using fMRI @DorinDaniil |
Natural scene reconstruction from fMRI signals using generative latent diffusion | 2023 | Furkan Ozcelik et al. | arXiv | GitHub | Use sklearn ridge regression as an fMRI encoder |
fMRI-based Decoding of Visual Information from Human Brain Activity: A Brief Review | 2021 | Shuo Huang et al. | Springer Link | - | Analyze architectures | |
Cinematic Mindscapes: High-quality Video Reconstruction from Brain Activity | 2023 | Zijiao Chen et al. | arXiv | GitHub, Website | TODO | |
High-resolution image reconstruction with latent diffusion models from human brain activity | 2023 | Yu Takagi et al. | arXiv | GitHub | ||
Methods using EEG @sem-k32 |
Visual Decoding and Reconstruction via EEG Embeddings with Guided Diffusion | 2024 | Dongyang Li et al. | arXiv | GitHub | EEG encoder = Transformer -> CNN (for spatiotemp. dependencies) -> MLP; EEG context vector is used to reconstruct image CLIP-vector. The latter is used in diffusion model to gen images |
NeuroGAN: image reconstruction from EEG signals via an attention-based GAN | 2022 | Rahul Mishra et al. | Springer Link | - | CNN encoder for EEG incorporated into GAN's generator. $$ Loss = Loss_{\text{GAN}} + Loss_{\text{image classification}} + Loss_{\text{perceptial loss}} $$ | |
EEG2IMAGE: Image Reconstruction from EEG Brain Signals | 2023 | Prajwal Singh et al. | arXiv | GitHub | Individual EEG feature extractor (LSTM, constastive learning) + conditioned GAN for image generation | |
Image Reconstruction from Electroencephalography Using Latent Diffusion | 2024 | Teng Fei et al. | arXiv | GitHub | info-gypsy | |
SOTA fMRI encoders @DorinDaniil |
||||||
SOTA EEG encoders @sem-k32 |
||||||
SOTA methods for image generation @kisnikser |
||||||