BrainDreamer: Reasoning-Coherent and Controllable Image Generation from EEG Brain Signals via Language Guidance

TL;DR

BrainDreamer is an innovative framework that translates EEG brain signals into high-quality, reasoning-coherent images guided by language, advancing brain-computer interface capabilities.

Contribution

It introduces a novel end-to-end model combining EEG-text-image alignment with controllable image generation, outperforming previous methods in quality and accuracy.

Findings

Superior image quality compared to prior methods

Effective noise reduction in EEG data

Enables controllable image generation from brain signals

Abstract

Can we directly visualize what we imagine in our brain together with what we describe? The inherent nature of human perception reveals that, when we think, our body can combine language description and build a vivid picture in our brain. Intuitively, generative models should also hold such versatility. In this paper, we introduce BrainDreamer, a novel end-to-end language-guided generative framework that can mimic human reasoning and generate high-quality images from electroencephalogram (EEG) brain signals. Our method is superior in its capacity to eliminate the noise introduced by non-invasive EEG data acquisition and meanwhile achieve a more precise mapping between the EEG and image modality, thus leading to significantly better-generated images. Specifically, BrainDreamer consists of two key learning stages: 1) modality alignment and 2) image generation. In the alignment stage, we propose a novel mask-based triple contrastive learning strategy to effectively align EEG, text, and image embeddings to learn a unified representation. In the generation stage, we inject the EEG embeddings into the pre-trained Stable Diffusion model by designing a learnable EEG adapter to generate high-quality reasoning-coherent images. Moreover, BrainDreamer can accept textual descriptions (e.g., color, position, etc.) to achieve controllable image generation. Extensive experiments show that our method significantly outperforms prior arts in terms of generating quality and quantitative performance.