# Multiscale Voxel Based Decoding For Enhanced Natural Image Reconstruction From Brain Activity

arXiv: https://arxiv.org/abs/2205.14177 · HTML: https://mlsanity.com/paper/2205.14177/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 25 references that are in the map.
- First posted on arXiv 27 May 2022.

## Builds on (most cited first, 9 of 9)

- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [Large Scale GAN Training for High Fidelity Natural Image Synthesis](https://mlsanity.com/paper/1809.11096/) (2018)
- [Conditional Generative Adversarial Nets](https://mlsanity.com/paper/1411.1784/) (2014)
- [A Neural Algorithm of Artistic Style](https://mlsanity.com/paper/1508.06576/) (2015)
- [Neural Style Transfer: A Review](https://mlsanity.com/paper/1705.04058/) (2017)
- [Generic decoding of seen and imagined objects using hierarchical visual features](https://mlsanity.com/paper/1510.06479/) (2015)
- [From voxels to pixels and back: Self-supervision in natural-image reconstruction from fMRI](https://mlsanity.com/paper/1907.02431/) (2019)
- [BigGAN-based Bayesian reconstruction of natural images from human brain activity](https://mlsanity.com/paper/2003.06105/) (2020)
- [Category decoding of visual stimuli from human brain activity using a bidirectional recurrent neural network to simulate bidirectional information flows in human visual cortices](https://mlsanity.com/paper/1903.07783/) (2019)

## Built on by (most cited first, 1 of 1)

- [Riemannian Geometry for the classification of brain states with intracortical brain-computer interfaces](https://mlsanity.com/paper/2504.05534/) (2025)

## Abstract (arXiv)

Reconstructing perceived images from human brain activity monitored by functional magnetic resonance imaging (fMRI) is hard, especially for natural images. Existing methods often result in blurry and unintelligible reconstructions with low fidelity. In this study, we present a novel approach for enhanced image reconstruction, in which existing methods for object decoding and image reconstruction are merged together. This is achieved by conditioning the reconstructed image to its decoded image category using a class-conditional generative adversarial network and neural style transfer. The results indicate that our approach improves the semantic similarity of the reconstructed images and can be used as a general framework for enhanced image reconstruction.