{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T11:28:06Z","timestamp":1780572486921,"version":"3.54.1"},"publisher-location":"Cham","reference-count":47,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031729829","type":"print"},{"value":"9783031729836","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T00:00:00Z","timestamp":1730160000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T00:00:00Z","timestamp":1730160000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-3-031-72983-6_4","type":"book-chapter","created":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T09:34:20Z","timestamp":1730108060000},"page":"56-73","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":13,"title":["NeuroPictor: Refining fMRI-to-Image Reconstruction via\u00a0Multi-individual Pretraining and\u00a0Multi-level Modulation"],"prefix":"10.1007","author":[{"given":"Jingyang","family":"Huo","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yikai","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yun","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xuelin","family":"Qian","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chong","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yanwei","family":"Fu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianfeng","family":"Feng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,10,29]]},"reference":[{"issue":"1","key":"4_CR1","doi-asserted-by":"publisher","first-page":"116","DOI":"10.1038\/s41593-021-00962-x","volume":"25","author":"EJ Allen","year":"2022","unstructured":"Allen, E.J., et al.: A massive 7t fMRI dataset to bridge cognitive neuroscience and artificial intelligence. Nat. Neurosci. 25(1), 116\u2013126 (2022)","journal-title":"Nat. Neurosci."},{"key":"4_CR2","unstructured":"Bar-Tal, O., Yariv, L., Lipman, Y., Dekel, T.: MultiDiffusion: fusing diffusion paths for controlled image generation. arXiv:2302.08113 (2023)"},{"key":"4_CR3","doi-asserted-by":"crossref","unstructured":"Bashkirova, D., Lezama, J., Sohn, K., Saenko, K., Essa, I.: MaskSketch: unpaired structure-guided masked image generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1879\u20131889 (2023)","DOI":"10.1109\/CVPR52729.2023.00187"},{"key":"4_CR4","doi-asserted-by":"crossref","unstructured":"Brooks, T., Holynski, A., Efros, A.A.: InstructPix2Pix: learning to follow image editing instructions. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18392\u201318402 (2023)","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"4_CR5","unstructured":"Caron, M., Misra, I., Mairal, J., Goyal, P., Bojanowski, P., Joulin, A.: Unsupervised learning of visual features by contrasting cluster assignments. In: Advances in Neural Information Processing Systems, vol. 33, pp. 9912\u20139924 (2020)"},{"issue":"1","key":"4_CR6","doi-asserted-by":"publisher","first-page":"49","DOI":"10.1038\/s41597-019-0052-3","volume":"6","author":"N Chang","year":"2019","unstructured":"Chang, N., Pyles, J.A., Marcus, A., Gupta, A., Tarr, M.J., Aminoff, E.M.: Bold5000, a public fMRI dataset while viewing 5000 visual images. Sci. Data 6(1), 49 (2019)","journal-title":"Sci. Data"},{"key":"4_CR7","doi-asserted-by":"crossref","unstructured":"Chen, Z., Qing, J., Xiang, T., Yue, W.L., Zhou, J.H.: Seeing beyond the brain: conditional diffusion model with sparse masked modeling for vision decoding. arXiv preprint arXiv:2211.06956 (2022)","DOI":"10.1109\/CVPR52729.2023.02175"},{"key":"4_CR8","doi-asserted-by":"crossref","unstructured":"Chen, Z., Qing, J., Xiang, T., Yue, W.L., Zhou, J.H.: Seeing beyond the brain: conditional diffusion model with sparse masked modeling for vision decoding. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 22710\u201322720 (2023)","DOI":"10.1109\/CVPR52729.2023.02175"},{"key":"4_CR9","unstructured":"Chen, Z., Qing, J., Zhou, J.H.: Cinematic mindscapes: high-quality video reconstruction from brain activity. arXiv preprint arXiv:2305.11675 (2023)"},{"issue":"2","key":"4_CR10","doi-asserted-by":"publisher","first-page":"261","DOI":"10.1016\/S1053-8119(03)00049-1","volume":"19","author":"DD Cox","year":"2003","unstructured":"Cox, D.D., Savoy, R.L.: Functional magnetic resonance imaging (FMRI) \u201cbrain reading\u2019\u2019: detecting and classifying distributed patterns of fMRI activity in human visual cortex. Neuroimage 19(2), 261\u2013270 (2003)","journal-title":"Neuroimage"},{"key":"4_CR11","doi-asserted-by":"crossref","unstructured":"Esser, P., Rombach, R., Ommer, B.: Taming transformers for high-resolution image synthesis. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2021, virtual, June 19\u201325, 2021, pp. 12873\u201312883. Computer Vision Foundation\/IEEE (2021)","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"4_CR12","unstructured":"Fang, T., Zheng, Q., Pan, G.: Alleviating the semantic gap for generalized fMRI-to-image reconstruction. In: Advances in Neural Information Processing Systems, vol. 36 (2024)"},{"key":"4_CR13","unstructured":"Ferrante, M., Ozcelik, F., Boccato, T., VanRullen, R., Toschi, N.: Brain captioning: decoding human brain activity into images and text. arXiv preprint arXiv:2305.11560 (2023)"},{"key":"4_CR14","unstructured":"Gal, R., et al.: An image is worth one word: personalizing text-to-image generation using textual inversion. arXiv preprint arXiv:2208.01618 (2022)"},{"issue":"2","key":"4_CR15","doi-asserted-by":"publisher","first-page":"133","DOI":"10.1016\/j.nec.2010.11.001","volume":"22","author":"GH Glover","year":"2011","unstructured":"Glover, G.H.: Overview of functional magnetic resonance imaging. Neurosurg. Clin. 22(2), 133\u2013139 (2011)","journal-title":"Neurosurg. Clin."},{"key":"4_CR16","unstructured":"Gu, Z., Jamison, K., Kuceyeski, A., Sabuncu, M.: Decoding natural image stimuli from fMRI data with a surface-based convolutional network. arXiv preprint arXiv:2212.02409 (2022)"},{"key":"4_CR17","doi-asserted-by":"publisher","first-page":"118812","DOI":"10.1016\/j.neuroimage.2021.118812","volume":"247","author":"Z Gu","year":"2022","unstructured":"Gu, Z., et al.: Neurogen: activation optimized image synthesis for discovery neuroscience. Neuroimage 247, 118812 (2022)","journal-title":"Neuroimage"},{"issue":"5539","key":"4_CR18","doi-asserted-by":"publisher","first-page":"2425","DOI":"10.1126\/science.1063736","volume":"293","author":"JV Haxby","year":"2001","unstructured":"Haxby, J.V., Gobbini, M.I., Furey, M.L., Ishai, A., Schouten, J.L., Pietrini, P.: Distributed and overlapping representations of faces and objects in ventral temporal cortex. Science 293(5539), 2425\u20132430 (2001)","journal-title":"Science"},{"key":"4_CR19","unstructured":"Ho, J., Salimans, T.: Classifier-free diffusion guidance. arXiv preprint arXiv:2207.12598 (2022)"},{"key":"4_CR20","unstructured":"Huang, L., Chen, D., Liu, Y., Shen, Y., Zhao, D., Zhou, J.: Composer: creative and controllable image synthesis with composable conditions. arXiv preprint arXiv:2302.09778 (2023)"},{"issue":"7185","key":"4_CR21","doi-asserted-by":"publisher","first-page":"352","DOI":"10.1038\/nature06713","volume":"452","author":"KN Kay","year":"2008","unstructured":"Kay, K.N., Naselaris, T., Prenger, R.J., Gallant, J.L.: Identifying natural images from human brain activity. Nature 452(7185), 352\u2013355 (2008)","journal-title":"Nature"},{"key":"4_CR22","unstructured":"Lin, S., Sprague, T., Singh, A.K.: Mind reader: reconstructing complex images from brain activities. In: Advances in Neural Information Processing Systems, vol. 35, pp. 29624\u201329636 (2022)"},{"key":"4_CR23","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T-Y Lin","year":"2014","unstructured":"Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"issue":"11","key":"4_CR24","doi-asserted-by":"publisher","first-page":"1523","DOI":"10.1038\/nn.4393","volume":"19","author":"KL Miller","year":"2016","unstructured":"Miller, K.L., et al.: Multimodal population brain imaging in the UK biobank prospective epidemiological study. Nat. Neurosci. 19(11), 1523\u20131536 (2016)","journal-title":"Nat. Neurosci."},{"key":"4_CR25","doi-asserted-by":"crossref","unstructured":"Mou, C., et al.: T2i-adapter: learning adapters to dig out more controllable ability for text-to-image diffusion models. arXiv preprint arXiv:2302.08453 (2023)","DOI":"10.1609\/aaai.v38i5.28226"},{"key":"4_CR26","doi-asserted-by":"crossref","unstructured":"Mozafari, M., Reddy, L., VanRullen, R.: Reconstructing natural scenes from fMRI patterns using BigBiGAN. In: 2020 International Joint Conference on Neural Networks, IJCNN 2020, Glasgow, United Kingdom, July 19\u201324, 2020, pp.\u00a01\u20138. IEEE (2020)","DOI":"10.1109\/IJCNN48605.2020.9206960"},{"key":"4_CR27","doi-asserted-by":"crossref","unstructured":"Ozcelik, F., VanRullen, R.: Brain-diffuser: natural scene reconstruction from fMRI signals using generative latent diffusion. arXiv preprint arXiv:2303.05334 (2023)","DOI":"10.1038\/s41598-023-42891-8"},{"issue":"1","key":"4_CR28","doi-asserted-by":"publisher","first-page":"15666","DOI":"10.1038\/s41598-023-42891-8","volume":"13","author":"F Ozcelik","year":"2023","unstructured":"Ozcelik, F., VanRullen, R.: Natural scene reconstruction from fMRI signals using generative latent diffusion. Sci. Rep. 13(1), 15666 (2023)","journal-title":"Sci. Rep."},{"key":"4_CR29","unstructured":"Qian, X., Wang, Y., Huo, J., Feng, J., Fu, Y.: fMRI-PTE: a large-scale fMRI pretrained transformer encoder for multi-subject brain activity decoding. arXiv preprint arXiv:2311.00342 (2023)"},{"key":"4_CR30","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"4_CR31","doi-asserted-by":"publisher","first-page":"117602","DOI":"10.1016\/j.neuroimage.2020.117602","volume":"228","author":"Z Ren","year":"2021","unstructured":"Ren, Z., et al.: Reconstructing seen image from brain activity by visually-guided cognitive representation and adversarial learning. Neuroimage 228, 117602 (2021)","journal-title":"Neuroimage"},{"key":"4_CR32","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10684\u201310695 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"4_CR33","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"234","DOI":"10.1007\/978-3-319-24574-4_28","volume-title":"Medical Image Computing and Computer-Assisted Intervention \u2013 MICCAI 2015","author":"O Ronneberger","year":"2015","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234\u2013241. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-24574-4_28"},{"key":"4_CR34","doi-asserted-by":"crossref","unstructured":"Ruiz, N., Li, Y., Jampani, V., Pritch, Y., Rubinstein, M., Aberman, K.: Dreambooth: fine tuning text-to-image diffusion models for subject-driven generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 22500\u201322510 (2023)","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"4_CR35","doi-asserted-by":"publisher","first-page":"951","DOI":"10.1016\/j.neuroimage.2013.07.043","volume":"83","author":"S Schoenmakers","year":"2013","unstructured":"Schoenmakers, S., Barth, M., Heskes, T., Van Gerven, M.: Linear reconstruction of perceived images from human brain activity. Neuroimage 83, 951\u2013961 (2013)","journal-title":"Neuroimage"},{"key":"4_CR36","unstructured":"Scotti, P.S., et\u00a0al.: Reconstructing the mind\u2019s eye: fMRI-to-image with contrastive learning and diffusion priors. arXiv preprint arXiv:2305.18274 (2023)"},{"key":"4_CR37","unstructured":"Scotti, P.S., et\u00a0al.: Mindeye2: shared-subject models enable fMRI-to-image with 1 hour of data. arXiv preprint arXiv:2403.11207 (2024)"},{"issue":"5500","key":"4_CR38","doi-asserted-by":"publisher","first-page":"2268","DOI":"10.1126\/science.290.5500.2268","volume":"290","author":"HS Seung","year":"2000","unstructured":"Seung, H.S., Lee, D.D.: The manifold ways of perception. Science 290(5500), 2268\u20132269 (2000)","journal-title":"Science"},{"issue":"1","key":"4_CR39","doi-asserted-by":"publisher","first-page":"e1006633","DOI":"10.1371\/journal.pcbi.1006633","volume":"15","author":"G Shen","year":"2019","unstructured":"Shen, G., Horikawa, T., Majima, K., Kamitani, Y.: Deep image reconstruction from human brain activity. PLoS Comput. Biol. 15(1), e1006633 (2019)","journal-title":"PLoS Comput. Biol."},{"key":"4_CR40","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2818\u20132826 (2016)","DOI":"10.1109\/CVPR.2016.308"},{"key":"4_CR41","doi-asserted-by":"crossref","unstructured":"Takagi, Y., Nishimoto, S.: High-resolution image reconstruction with latent diffusion models from human brain activity. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14453\u201314463 (2023)","DOI":"10.1109\/CVPR52729.2023.01389"},{"key":"4_CR42","unstructured":"Tan, M., Le, Q.: EfficientNet: rethinking model scaling for convolutional neural networks. In: International Conference on Machine Learning, pp. 6105\u20136114. PMLR (2019)"},{"issue":"4","key":"4_CR43","doi-asserted-by":"publisher","first-page":"1104","DOI":"10.1016\/j.neuroimage.2006.06.062","volume":"33","author":"B Thirion","year":"2006","unstructured":"Thirion, B., et al.: Inverse retinotopy: inferring the visual content of images from brain activation patterns. Neuroimage 33(4), 1104\u20131116 (2006)","journal-title":"Neuroimage"},{"issue":"4","key":"4_CR44","doi-asserted-by":"publisher","first-page":"600","DOI":"10.1109\/TIP.2003.819861","volume":"13","author":"Z Wang","year":"2004","unstructured":"Wang, Z., Bovik, A.C., Sheikh, H.R., Simoncelli, E.P.: Image quality assessment: from error visibility to structural similarity. IEEE Trans. Image Process. 13(4), 600\u2013612 (2004)","journal-title":"IEEE Trans. Image Process."},{"key":"4_CR45","doi-asserted-by":"crossref","unstructured":"Xu, X., Wang, Z., Zhang, G., Wang, K., Shi, H.: Versatile diffusion: text, images and variations all in one diffusion model. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 7754\u20137765 (2023)","DOI":"10.1109\/ICCV51070.2023.00713"},{"key":"4_CR46","unstructured":"Zeng, B., et al.: Controllable mind visual diffusion model. arXiv preprint arXiv:2305.10135 (2023)"},{"key":"4_CR47","doi-asserted-by":"crossref","unstructured":"Zhang, L., Rao, A., Agrawala, M.: Adding conditional control to text-to-image diffusion models. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3836\u20133847 (2023)","DOI":"10.1109\/ICCV51070.2023.00355"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-72983-6_4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T09:55:40Z","timestamp":1730109340000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72983-6_4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,29]]},"ISBN":["9783031729829","9783031729836"],"references-count":47,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72983-6_4","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,29]]},"assertion":[{"value":"29 October 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}