Cinematic Mindscapes: High-quality Video Reconstruction from Brain Activity

TL;DR

This paper introduces Mind-Video, a novel method for reconstructing high-quality, continuous videos from brain activity data, advancing understanding of visual cognition and improving video reconstruction accuracy.

Contribution

Mind-Video is the first approach to learn spatiotemporal information from continuous fMRI data for video reconstruction, integrating masked brain modeling and multimodal contrastive learning.

Findings

Achieved 85% accuracy in semantic classification tasks

Attained 0.19 SSIM, surpassing previous methods by 45%

Produced high-quality videos at arbitrary frame rates

Abstract

Reconstructing human vision from brain activities has been an appealing task that helps to understand our cognitive process. Even though recent research has seen great success in reconstructing static images from non-invasive brain recordings, work on recovering continuous visual experiences in the form of videos is limited. In this work, we propose Mind-Video that learns spatiotemporal information from continuous fMRI data of the cerebral cortex progressively through masked brain modeling, multimodal contrastive learning with spatiotemporal attention, and co-training with an augmented Stable Diffusion model that incorporates network temporal inflation. We show that high-quality videos of arbitrary frame rates can be reconstructed with Mind-Video using adversarial guidance. The recovered videos were evaluated with various semantic and pixel-level metrics. We achieved an average accuracy of 85% in semantic classification tasks and 0.19 in structural similarity index (SSIM), outperforming the previous state-of-the-art by 45%. We also show that our model is biologically plausible and interpretable, reflecting established physiological processes.