BrainVis: Exploring the Bridge between Brain and Visual Signals via Image Reconstruction
This work addresses the challenge of improving visual reconstruction from brain signals for neuroscience and brain-computer interface applications, representing an incremental advance with specific gains.
The paper tackles the problem of reconstructing visual stimuli from noisy EEG signals by proposing BrainVis, a method that aligns EEG time-frequency embeddings with semantic information in CLIP space and uses cascaded diffusion models, achieving state-of-the-art performance in semantic fidelity and generation quality with only 10% of the training data used in prior work.
Analyzing and reconstructing visual stimuli from brain signals effectively advances the understanding of human visual system. However, the EEG signals are complex and contain significant noise. This leads to substantial limitations in existing works of visual stimuli reconstruction from EEG, such as difficulties in aligning EEG embeddings with the fine-grained semantic information and a heavy reliance on additional large self-collected dataset for training. To address these challenges, we propose a novel approach called BrainVis. Firstly, we divide the EEG signals into various units and apply a self-supervised approach on them to obtain EEG time-domain features, in an attempt to ease the training difficulty. Additionally, we also propose to utilize the frequency-domain features to enhance the EEG representations. Then, we simultaneously align EEG time-frequency embeddings with the interpolation of the coarse and fine-grained semantics in the CLIP space, to highlight the primary visual components and reduce the cross-modal alignment difficulty. Finally, we adopt the cascaded diffusion models to reconstruct images. Using only 10\% training data of the previous work, our proposed BrainVis outperforms state of the arts in both semantic fidelity reconstruction and generation quality. The code is available at https://github.com/RomGai/BrainVis.