Connecting dreams with visual brainstorming instructionOA
Recent breakthroughs in understanding the human brain have revealed its impressive ability to efficiently process and interpret human thoughts,opening up the possibility of intervening in brain signals.In this paper,we aim to develop a straightforward framework that uses other modalities,such as natural language,to translate the original“dreamland”.We present DreamConnect,employing a dual-stream diffusion framework to manipulate visually stimulated brain signals.By integrating an asynchronous diffusion strategy,our framework establishes an effective interface with human“dreams”,and progressively refines their final image synthesis.Through extensive experiments,we demonstrate the efficacy of our method to accurately direct human brain signals in desired directions,ultimately enabling concept manipulation through direct manipulation of the functional magnetic resonance imaging(fMRI)signals.We hope that this work will motivate the use of brain signals in human-computer interaction applications.
Yasheng Sun;Bohan Li;Mingchen Zhuge;Deng-Ping Fan;Salman Khan;Fahad Shahbaz Khan;Hideki Koike
School of Computing,Tokyo Institute of Technology,Tokyo 152-8550,JapanCollege of Computer Science,Shanghai Jiao Tong University,Shanghai 200240,ChinaCenter of Excellence for Generative AI,KAUST,Thuwal 23955-6900,Saudi ArabiaCollege of Computer Science,Nankai University,Tianjin 300350,ChinaComputer Vision Group,MBZUAI,Abu Dhabi 20015,UAEComputer Vision Group,MBZUAI,Abu Dhabi 20015,UAESchool of Computing,Tokyo Institute of Technology,Tokyo 152-8550,Japan
医药卫生
Functional magnetic resonance imaging(fMRI)Brain-to-image generationDiffusion modelsLarge language model(LLM)
《Visual Intelligence》 2025 (1)
P.165-182,18
supported by the National Natural Science Foundation of China(No.62476143).
评论