This paper introduces DreamDiffusion, a novel method for generating high-quality images directly from brain electroencephalogram (EEG) signals, without the need to translate thoughts into text. DreamDiffusion leverages pre-trained text-to-image models and employs temporal masked signal modeling to pre-train the EEG encoder for effective and robust EEG representations. Additionally, the method further leverages the CLIP image encoder to provide extra supervision to better align EEG, text, and image embeddings with limited EEG-image pairs. Overall, the proposed method overcomes the challenges of using EEG signals for image generation, such as noise, limited information, and individual differences, and achieves promising results. Quantitative and qualitative results demonstrate the effectiveness of the proposed method as a significant step towards portable and low-cost ``thoughts-to-image'', with potential applications in neuroscience and computer vision. The code is available here \url{https://github.com/bbaaii/DreamDiffusion}.

翻译：本文提出DreamDiffusion，一种直接从脑电信号生成高质量图像的新方法，无需将思维转化为文本。该方法利用预训练的文本到图像模型，并采用时序掩码信号建模预训练脑电编码器，以获得有效且鲁棒的脑电表征。此外，该方法进一步利用CLIP图像编码器提供额外监督，以在有限的脑电-图像配对数据下更好地对齐脑电、文本和图像嵌入。总体而言，该方法克服了利用脑电信号进行图像生成所面临的噪声、信息有限及个体差异等挑战，并取得了有前景的结果。定量与定性结果证明了该方法的有效性，是迈向便携、低成本的“思维到图像”的重要一步，在神经科学和计算机视觉领域具有潜在应用价值。代码见：\url{https://github.com/bbaaii/DreamDiffusion}。