paper-with-me

Papers

DreamDiffusion: Generating High-Quality Images from Brain EEG Signals

2023-06-29 · Yunpeng Bai, Xintao Wang, Yan-Pei Cao, Yixiao Ge, Chun Yuan, Ying Shan

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}.

📄 PDF Abstract BibTeX arXiv:2306.16934

Code (1)

bbaaii/DreamDiffusion 공식 구현 pytorch

Tasks

EEGElectroencephalogram (EEG)Image Generation

Methods 이 논문이 사용한 방법론

ALIGN In the ALIGN method, visual and language representations are jointly trained from noisy image alt-text data. The image and text encoders are learned via contrastive loss…
CLIP Contrastive Language-Image Pre-training (CLIP), consisting of a simplified version of ConVIRT trained from scratch, is an efficient method of image representation learning…

Similar Papers 제목 키워드 기반

A Novel Approach to Image EEG Sleep Data for Improving Quality of Life in Patients Suffering From Brain Injuries Using DreamDiffusion

2024-07-02 · David Fahim, Joshveer Grewal, Ritvik Ellendula

Those experiencing strokes, traumatic brain injuries, and drug complications can often end up hospitalized and diagnosed with coma or locked-in syndrome. Such mental impediments can permanently alter the neurological pat…

EEG

SYNAPSE: Synergizing an Adapter and Finetuning for High-Fidelity EEG Synthesis from a CLIP-Aligned Encoder

2025-11-11 · Jeyoung Lee, Hochul Kang arxiv

Recent progress in diffusion-based generative models has enabled high-quality image synthesis conditioned on diverse modalities. Extending such models to brain signals could deepen our understanding of human perception a…

Representation LearningImage Generation

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

2024-09-21 · Ling Wang, Chen Wu, Lin Wang

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 pict…

Contrastive LearningEEGElectroencephalogram (EEG)Image Generation

Non-Reference Quality Assessment for Medical Imaging: Application to Synthetic Brain MRIs

2024-07-20 · Karl Van Eeden Risager, Torkan Gholamalizadeh, Mostafa Mehdipour Ghazi

Generating high-quality synthetic data is crucial for addressing challenges in medical imaging, such as domain adaptation, data scarcity, and privacy concerns. Existing image quality metrics often rely on reference image…

BenchmarkingDomain Adaptation

Decoding Realistic Images from Brain Activity with Contrastive Self-supervision and Latent Diffusion

2023-09-30 · Jingyuan Sun, Mingxiao Li, Marie-Francine Moens

Reconstructing visual stimuli from human brain activities provides a promising opportunity to advance our understanding of the brain's visual system and its connection with computer vision models. Although deep generativ…

Contrastive Learning