Connecting dreams with visual brainstorming instruction

Abstract 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...

Full description

Saved in:
Bibliographic Details
Main Authors: Yasheng Sun, Bohan Li, Mingchen Zhuge, Deng-Ping Fan, Salman Khan, Fahad Shahbaz Khan, Hideki Koike
Format: Article
Language:English
Published: Springer 2025-07-01
Series:Visual Intelligence
Subjects:
Online Access:https://doi.org/10.1007/s44267-025-00081-2
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849238246382370816
author Yasheng Sun
Bohan Li
Mingchen Zhuge
Deng-Ping Fan
Salman Khan
Fahad Shahbaz Khan
Hideki Koike
author_facet Yasheng Sun
Bohan Li
Mingchen Zhuge
Deng-Ping Fan
Salman Khan
Fahad Shahbaz Khan
Hideki Koike
author_sort Yasheng Sun
collection DOAJ
description Abstract 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.
format Article
id doaj-art-b3572b8768fc40a7b6b7c1c331a14b93
institution Kabale University
issn 2097-3330
2731-9008
language English
publishDate 2025-07-01
publisher Springer
record_format Article
series Visual Intelligence
spelling doaj-art-b3572b8768fc40a7b6b7c1c331a14b932025-08-20T04:01:42ZengSpringerVisual Intelligence2097-33302731-90082025-07-013111810.1007/s44267-025-00081-2Connecting dreams with visual brainstorming instructionYasheng Sun0Bohan Li1Mingchen Zhuge2Deng-Ping Fan3Salman Khan4Fahad Shahbaz Khan5Hideki Koike6School of Computing, Tokyo Institute of TechnologyCollege of Computer Science, Shanghai Jiao Tong UniversityCenter of Excellence for Generative AI, KAUSTCollege of Computer Science, Nankai UniversityComputer Vision Group, MBZUAIComputer Vision Group, MBZUAISchool of Computing, Tokyo Institute of TechnologyAbstract 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.https://doi.org/10.1007/s44267-025-00081-2Functional magnetic resonance imaging (fMRI)Brain-to-image generationDiffusion modelsLarge language model (LLM)
spellingShingle Yasheng Sun
Bohan Li
Mingchen Zhuge
Deng-Ping Fan
Salman Khan
Fahad Shahbaz Khan
Hideki Koike
Connecting dreams with visual brainstorming instruction
Visual Intelligence
Functional magnetic resonance imaging (fMRI)
Brain-to-image generation
Diffusion models
Large language model (LLM)
title Connecting dreams with visual brainstorming instruction
title_full Connecting dreams with visual brainstorming instruction
title_fullStr Connecting dreams with visual brainstorming instruction
title_full_unstemmed Connecting dreams with visual brainstorming instruction
title_short Connecting dreams with visual brainstorming instruction
title_sort connecting dreams with visual brainstorming instruction
topic Functional magnetic resonance imaging (fMRI)
Brain-to-image generation
Diffusion models
Large language model (LLM)
url https://doi.org/10.1007/s44267-025-00081-2
work_keys_str_mv AT yashengsun connectingdreamswithvisualbrainstorminginstruction
AT bohanli connectingdreamswithvisualbrainstorminginstruction
AT mingchenzhuge connectingdreamswithvisualbrainstorminginstruction
AT dengpingfan connectingdreamswithvisualbrainstorminginstruction
AT salmankhan connectingdreamswithvisualbrainstorminginstruction
AT fahadshahbazkhan connectingdreamswithvisualbrainstorminginstruction
AT hidekikoike connectingdreamswithvisualbrainstorminginstruction