https://twitter.com/kencan7749/status/1684034967247151107?s=20

\n","updatedAt":"2023-08-08T11:31:56.111Z","author":{"_id":"61191fb6d3c7a4ea2d9c8b38","avatarUrl":"/avatars/004c1e03f88da32e3baf5faf854a11e0.svg","fullname":"Yukiyasu Kamitani","name":"ykamit","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.3445061445236206},"editors":["ykamit"],"editorAvatarUrls":["/avatars/004c1e03f88da32e3baf5faf854a11e0.svg"],"reactions":[{"reaction":"🤝","users":["ozyman"],"count":1}],"isReport":false}},{"id":"64d66c93dd57652c1a5f6250","author":{"_id":"62fb5f53f60cc3ae07393f4e","avatarUrl":"/avatars/a96c55b362f477cdb2d5feca42629cf5.svg","fullname":"Mobin Chowdhury","name":"mobinx","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":3,"isUserFollowing":false},"createdAt":"2023-08-11T17:14:59.000Z","type":"comment","data":{"edited":false,"hidden":false,"latest":{"raw":"Interesting","html":"

Interesting

\n","updatedAt":"2023-08-11T17:14:59.183Z","author":{"_id":"62fb5f53f60cc3ae07393f4e","avatarUrl":"/avatars/a96c55b362f477cdb2d5feca42629cf5.svg","fullname":"Mobin Chowdhury","name":"mobinx","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":3,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.6707755327224731},"editors":["mobinx"],"editorAvatarUrls":["/avatars/a96c55b362f477cdb2d5feca42629cf5.svg"],"reactions":[],"isReport":false}}],"primaryEmailConfirmed":false,"paper":{"id":"2308.02510","authors":[{"_id":"64d1d53b44d373d7067453ac","name":"Yu-Ting Lan","hidden":false},{"_id":"64d1d53b44d373d7067453ad","name":"Kan Ren","hidden":false},{"_id":"64d1d53b44d373d7067453ae","name":"Yansen Wang","hidden":false},{"_id":"64d1d53b44d373d7067453af","name":"Wei-Long Zheng","hidden":false},{"_id":"64d1d53b44d373d7067453b0","name":"Dongsheng Li","hidden":false},{"_id":"64d1d53b44d373d7067453b1","name":"Bao-Liang Lu","hidden":false},{"_id":"64d1d53b44d373d7067453b2","name":"Lili Qiu","hidden":false}],"publishedAt":"2023-07-27T12:54:16.000Z","submittedOnDailyAt":"2023-08-08T04:10:12.099Z","title":"Seeing through the Brain: Image Reconstruction of Visual Perception from\n Human Brain Signals","submittedOnDailyBy":{"_id":"60f1abe7544c2adfd699860c","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1674929746905-60f1abe7544c2adfd699860c.jpeg","isPro":false,"fullname":"AK","user":"akhaliq","type":"user"},"summary":"Seeing is believing, however, the underlying mechanism of how human visual\nperceptions are intertwined with our cognitions is still a mystery. Thanks to\nthe recent advances in both neuroscience and artificial intelligence, we have\nbeen able to record the visually evoked brain activities and mimic the visual\nperception ability through computational approaches. In this paper, we pay\nattention to visual stimuli reconstruction by reconstructing the observed\nimages based on portably accessible brain signals, i.e., electroencephalography\n(EEG) data. Since EEG signals are dynamic in the time-series format and are\nnotorious to be noisy, processing and extracting useful information requires\nmore dedicated efforts; In this paper, we propose a comprehensive pipeline,\nnamed NeuroImagen, for reconstructing visual stimuli images from EEG signals.\nSpecifically, we incorporate a novel multi-level perceptual information\ndecoding to draw multi-grained outputs from the given EEG data. A latent\ndiffusion model will then leverage the extracted information to reconstruct the\nhigh-resolution visual stimuli images. The experimental results have\nillustrated the effectiveness of image reconstruction and superior quantitative\nperformance of our proposed method.","upvotes":23,"discussionId":"64d1d53c44d373d7067453c1","ai_summary":"A pipeline named NeuroImagen uses EEG signals and a latent diffusion model to reconstruct high-resolution visual images, demonstrating superior performance in image reconstruction.","ai_keywords":["visual stimuli reconstruction","electroencephalography","EEG","multi-level perceptual information decoding","latent diffusion model","high-resolution visual stimuli images"]},"canReadDatabase":false,"canManagePapers":false,"canSubmit":false,"hasHfLevelAccess":false,"upvoted":false,"upvoters":[{"_id":"6538119803519fddb4a17e10","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/6538119803519fddb4a17e10/ffJMkdx-rM7VvLTCM6ri_.jpeg","isPro":false,"fullname":"samusenps","user":"samusenps","type":"user"},{"_id":"64b183300a54158d66dd3587","avatarUrl":"/avatars/55ee1f1a0bf57a9d045e739f6dbbaeed.svg","isPro":false,"fullname":"Rocl Jamez","user":"James62","type":"user"},{"_id":"63044d41d14428368d1cac3d","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1675335466846-63044d41d14428368d1cac3d.png","isPro":false,"fullname":"Alisher Amantay","user":"ozyman","type":"user"},{"_id":"64408cd43e0374802e19f454","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/64408cd43e0374802e19f454/nOnDGGBF0p-AwkCGw0IZh.png","isPro":false,"fullname":"Darrel Bryan","user":"ZeroXClem","type":"user"},{"_id":"64a6b481b1f875f03fa258e4","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/64a6b481b1f875f03fa258e4/NZ3nV4CWwi3ZpoZXpTgD_.png","isPro":false,"fullname":"Ahmed Allam","user":"ahmedallam","type":"user"},{"_id":"6303d5350907b9a115c42a5f","avatarUrl":"/avatars/eba35bf756ae1703e10cace3aa6674a5.svg","isPro":false,"fullname":"Elad Yundler","user":"elad619","type":"user"},{"_id":"5dd96eb166059660ed1ee413","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/5dd96eb166059660ed1ee413/NQtzmrDdbG0H8qkZvRyGk.jpeg","isPro":true,"fullname":"Julien Chaumond","user":"julien-c","type":"user"},{"_id":"63d4c8ce13ae45b780792f32","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/63d4c8ce13ae45b780792f32/QasegimoxBqfZwDzorukz.png","isPro":false,"fullname":"Ohenenoo","user":"PeepDaSlan9","type":"user"},{"_id":"6392e5cf6d2eaf66e4677c79","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1670571359184-noauth.png","isPro":false,"fullname":"Arman Haghighi K.","user":"armanhk","type":"user"},{"_id":"63386fc5768611eccab34c17","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/63386fc5768611eccab34c17/tqQHl9boPXdnVjWMlP1er.png","isPro":false,"fullname":"Psy Eyes","user":"PsyEyes","type":"user"},{"_id":"6311e01bd5a165db5d1f683e","avatarUrl":"/avatars/5d77041d5524e52621ce4ca1597de9b3.svg","isPro":false,"fullname":"Samuel Gyamfi","user":"Onlyartist9","type":"user"},{"_id":"6276eb032c670b8e9d7de2d7","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/6276eb032c670b8e9d7de2d7/Z_Dk0Ki3IBdWrfOn5llgL.jpeg","isPro":false,"fullname":"Antoine Bellion","user":"abellion","type":"user"}],"acceptLanguages":["*"],"dailyPaperRank":0}">

Papers

arxiv:2308.02510

Seeing through the Brain: Image Reconstruction of Visual Perception from Human Brain Signals

Published on Jul 27, 2023

· Submitted by

AK on Aug 8, 2023

Upvote

Authors:

Abstract

A pipeline named NeuroImagen uses EEG signals and a latent diffusion model to reconstruct high-resolution visual images, demonstrating superior performance in image reconstruction.

AI-generated summary

Seeing is believing, however, the underlying mechanism of how human visual perceptions are intertwined with our cognitions is still a mystery. Thanks to the recent advances in both neuroscience and artificial intelligence, we have been able to record the visually evoked brain activities and mimic the visual perception ability through computational approaches. In this paper, we pay attention to visual stimuli reconstruction by reconstructing the observed images based on portably accessible brain signals, i.e., electroencephalography (EEG) data. Since EEG signals are dynamic in the time-series format and are notorious to be noisy, processing and extracting useful information requires more dedicated efforts; In this paper, we propose a comprehensive pipeline, named NeuroImagen, for reconstructing visual stimuli images from EEG signals. Specifically, we incorporate a novel multi-level perceptual information decoding to draw multi-grained outputs from the given EEG data. A latent diffusion model will then leverage the extracted information to reconstruct the high-resolution visual stimuli images. The experimental results have illustrated the effectiveness of image reconstruction and superior quantitative performance of our proposed method.

View arXiv page View PDF Add to collection

Community

ozyman

Aug 8, 2023

Always interesting to hear about brain signals using some hyping architectures. Do they use the actual images (captured say from gopro) seen by people as the true labels?