{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,14]],"date-time":"2026-06-14T09:28:16Z","timestamp":1781429296885,"version":"3.54.1"},"publisher-location":"Cham","reference-count":55,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031729690","type":"print"},{"value":"9783031729706","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,23]],"date-time":"2024-11-23T00:00:00Z","timestamp":1732320000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,23]],"date-time":"2024-11-23T00:00:00Z","timestamp":1732320000000},"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\/978-3-031-72970-6_18","type":"book-chapter","created":{"date-parts":[[2024,11,22]],"date-time":"2024-11-22T10:50:32Z","timestamp":1732272632000},"page":"312-329","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["MinD-3D: Reconstruct High-Quality 3D Objects in\u00a0Human Brain"],"prefix":"10.1007","author":[{"given":"Jianxiong","family":"Gao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuqian","family":"Fu","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":"Jianfeng","family":"Feng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yanwei","family":"Fu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,11,23]]},"reference":[{"issue":"1","key":"18_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":"18_CR2","unstructured":"Chang, A.X., et\u00a0al.: ShapeNet: an information-rich 3D model repository. arXiv preprint arXiv:1512.03012 (2015)"},{"key":"18_CR3","doi-asserted-by":"crossref","unstructured":"Chang, H., Zhang, H., Jiang, L., Liu, C., Freeman, W.T.: MaskGIT: masked generative image transformer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11315\u201311325 (2022)","DOI":"10.1109\/CVPR52688.2022.01103"},{"issue":"1","key":"18_CR4","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":"18_CR5","doi-asserted-by":"crossref","unstructured":"Chen, Z., Zhang, H.: Learning implicit fields for generative shape modeling. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5939\u20135948 (2019)","DOI":"10.1109\/CVPR.2019.00609"},{"key":"18_CR6","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":"18_CR7","unstructured":"Chen, Z., Qing, J., Zhou, J.H.: Cinematic mindscapes: high-quality video reconstruction from brain activity. arXiv preprint arXiv:2305.11675 (2023)"},{"key":"18_CR8","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"89","DOI":"10.1007\/978-3-031-20062-5_6","volume-title":"ECCV 2022","author":"AC Cheng","year":"2022","unstructured":"Cheng, A.C., Li, X., Liu, S., Sun, M., Yang, M.H.: Autoregressive 3D shape generation via canonical mapping. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13663, pp. 89\u2013104. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20062-5_6"},{"key":"18_CR9","doi-asserted-by":"crossref","unstructured":"Cherti, M., et al.: Reproducible scaling laws for contrastive language-image learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2818\u20132829 (2023)","DOI":"10.1109\/CVPR52729.2023.00276"},{"issue":"5","key":"18_CR10","doi-asserted-by":"publisher","first-page":"948","DOI":"10.1016\/j.eng.2019.03.010","volume":"5","author":"C Du","year":"2019","unstructured":"Du, C., Li, J., Huang, L., He, H.: Brain encoding and decoding in fMRI with bidirectional deep generative models. Engineering 5(5), 948\u2013953 (2019)","journal-title":"Engineering"},{"key":"18_CR11","doi-asserted-by":"publisher","unstructured":"Esteban, O., et al.: fMRIPrep. Software (2018). https:\/\/doi.org\/10.5281\/zenodo.852659","DOI":"10.5281\/zenodo.852659"},{"key":"18_CR12","doi-asserted-by":"publisher","first-page":"111","DOI":"10.1038\/s41592-018-0235-4","volume":"16","author":"O Esteban","year":"2019","unstructured":"Esteban, O., et al.: fMRIPrep: a robust preprocessing pipeline for functional MRI. Nat. Methods 16, 111\u2013116 (2019). https:\/\/doi.org\/10.1038\/s41592-018-0235-4","journal-title":"Nat. Methods"},{"key":"18_CR13","doi-asserted-by":"crossref","unstructured":"Gao, J., et al.: Coarse-to-fine amodal segmentation with shape prior. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 1262\u20131271 (2023)","DOI":"10.1109\/ICCV51070.2023.00122"},{"issue":"3","key":"18_CR14","doi-asserted-by":"publisher","first-page":"727","DOI":"10.1523\/JNEUROSCI.4753-08.2009","volume":"29","author":"S Georgieva","year":"2009","unstructured":"Georgieva, S., Peeters, R., Kolster, H., Todd, J.T., Orban, G.A.: The processing of three-dimensional shape from disparity in the human brain. J. Neurosci. 29(3), 727\u2013742 (2009)","journal-title":"J. Neurosci."},{"issue":"1","key":"18_CR15","doi-asserted-by":"publisher","first-page":"8","DOI":"10.1016\/j.neuron.2018.12.014","volume":"101","author":"II Groen","year":"2019","unstructured":"Groen, I.I., Baker, C.I.: Scenes in the human brain: comparing 2D versus 3D representations. Neuron 101(1), 8\u201310 (2019)","journal-title":"Neuron"},{"key":"18_CR16","doi-asserted-by":"publisher","unstructured":"Grossberg, S.: 370 How we see the world in depth: from 3D vision to how 2D pictures induce 3D percepts. In: Conscious Mind, Resonant Brain: How Each Brain Makes a Mind. Oxford University Press (2021). https:\/\/doi.org\/10.1093\/oso\/9780190070557.003.0011","DOI":"10.1093\/oso\/9780190070557.003.0011"},{"key":"18_CR17","doi-asserted-by":"crossref","unstructured":"He, K., Chen, X., Xie, S., Li, Y., Doll\u00e1r, P., Girshick, R.: Masked autoencoders are scalable vision learners. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16000\u201316009 (2022)","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"18_CR18","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. In: Advances in Neural Information Processing Systems, vol. 33, pp. 6840\u20136851 (2020)"},{"issue":"1","key":"18_CR19","doi-asserted-by":"publisher","first-page":"15037","DOI":"10.1038\/ncomms15037","volume":"8","author":"T Horikawa","year":"2017","unstructured":"Horikawa, T., Kamitani, Y.: Generic decoding of seen and imagined objects using hierarchical visual features. Nat. Commun. 8(1), 15037 (2017)","journal-title":"Nat. Commun."},{"key":"18_CR20","unstructured":"Houlsby, N., et al.: Parameter-efficient transfer learning for NLP. In: International Conference on Machine Learning, pp. 2790\u20132799. PMLR (2019)"},{"key":"18_CR21","doi-asserted-by":"crossref","unstructured":"Ibing, M., Kobsik, G., Kobbelt, L.: Octree transformer: autoregressive 3D shape generation on hierarchically structured sequences. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2698\u20132707 (2023)","DOI":"10.1109\/CVPRW59228.2023.00270"},{"key":"18_CR22","doi-asserted-by":"crossref","unstructured":"Ibing, M., Lim, I., Kobbelt, L.: 3D shape generation with grid-based implicit functions. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13559\u201313568 (2021)","DOI":"10.1109\/CVPR46437.2021.01335"},{"issue":"1","key":"18_CR23","doi-asserted-by":"publisher","first-page":"45","DOI":"10.1016\/j.jmhi.2015.02.001","volume":"9","author":"R Jerath","year":"2015","unstructured":"Jerath, R., Crawford, M.W., Barnes, V.A.: Functional representation of vision within the mind: a visual consciousness model based in 3D default space. J. Med. Hypotheses Ideas 9(1), 45\u201356 (2015)","journal-title":"J. Med. Hypotheses Ideas"},{"key":"18_CR24","doi-asserted-by":"crossref","unstructured":"Kerbl, B., Kopanas, G., Leimk\u00fchler, T., Drettakis, G.: 3D Gaussian splatting for real-time radiance field rendering. ACM Trans. Graph. 42(4) (2023). https:\/\/repo-sam.inria.fr\/fungraph\/3d-gaussian-splatting\/","DOI":"10.1145\/3592433"},{"issue":"1869","key":"18_CR25","doi-asserted-by":"publisher","first-page":"20210455","DOI":"10.1098\/rstb.2021.0455","volume":"378","author":"P Linton","year":"2023","unstructured":"Linton, P.: Minimal theory of 3D vision: new approach to visual scale and visual shape. Philos. Trans. R. Soc. B 378(1869), 20210455 (2023)","journal-title":"Philos. Trans. R. Soc. B"},{"key":"18_CR26","doi-asserted-by":"crossref","unstructured":"Liu, J., et\u00a0al.: MirrorGaussian: reflecting 3D Gaussians for reconstructing mirror reflections. arXiv preprint arXiv:2405.11921 (2024)","DOI":"10.1007\/978-3-031-73220-1_22"},{"key":"18_CR27","doi-asserted-by":"crossref","unstructured":"Liu, R., Wu, R., Hoorick, B.V., Tokmakov, P., Zakharov, S., Vondrick, C.: Zero-1-to-3: zero-shot one image to 3D object (2023)","DOI":"10.1109\/ICCV51070.2023.00853"},{"key":"18_CR28","doi-asserted-by":"crossref","unstructured":"Liu, Z., Wang, Y., Qi, X., Fu, C.W.: Towards implicit text-guided 3D shape generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 17896\u201317906 (2022)","DOI":"10.1109\/CVPR52688.2022.01737"},{"key":"18_CR29","unstructured":"Mai, W., Zhang, Z.: Unibrain: unify image reconstruction and captioning all in one diffusion model from human brain activity. arXiv preprint arXiv:2308.07428 (2023)"},{"issue":"11","key":"18_CR30","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":"18_CR31","doi-asserted-by":"crossref","unstructured":"Ozcelik, F., Choksi, B., Mozafari, M., Reddy, L., VanRullen, R.: Reconstruction of perceived images from fMRI patterns and semantic brain exploration using instance-conditioned GANs. In: 2022 International Joint Conference on Neural Networks (IJCNN), pp.\u00a01\u20138. IEEE (2022)","DOI":"10.1109\/IJCNN55064.2022.9892673"},{"key":"18_CR32","doi-asserted-by":"crossref","unstructured":"Peebles, W., Xie, S.: Scalable diffusion models with transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4195\u20134205 (2023)","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"18_CR33","unstructured":"Qian, X., Wang, Y., Fu, Y., Xue, X., Feng, J.: Semantic neural decoding via cross-modal generation. arXiv preprint arXiv:2303.14730 (2023)"},{"key":"18_CR34","unstructured":"Qian, X., et\u00a0al.: Pushing auto-regressive models for 3D shape generation at capacity and scalability. arXiv preprint arXiv:2402.12225 (2024)"},{"key":"18_CR35","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":"18_CR36","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":"18_CR37","unstructured":"Ramesh, A., Dhariwal, P., Nichol, A., Chu, C., Chen, M.: Hierarchical text-conditional image generation with clip latents. arXiv preprint arXiv:2204.06125, 1(2), 3 (2022)"},{"key":"18_CR38","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models (2021)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"18_CR39","doi-asserted-by":"crossref","unstructured":"Sargent, K., et\u00a0al.: ZeroNVS: zero-shot 360-degree view synthesis from a single real image. arXiv preprint arXiv:2310.17994 (2023)","DOI":"10.1109\/CVPR52733.2024.00900"},{"key":"18_CR40","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":"18_CR41","doi-asserted-by":"publisher","first-page":"21","DOI":"10.3389\/fncom.2019.00021","volume":"13","author":"G Shen","year":"2019","unstructured":"Shen, G., Dwivedi, K., Majima, K., Horikawa, T., Kamitani, Y.: End-to-end deep image reconstruction from human brain activity. Front. Comput. Neurosci. 13, 21 (2019)","journal-title":"Front. Comput. Neurosci."},{"issue":"1","key":"18_CR42","doi-asserted-by":"publisher","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":"18_CR43","unstructured":"Song, J., Meng, C., Ermon, S.: Denoising diffusion implicit models. arXiv preprint arXiv:2010.02502 (2020)"},{"key":"18_CR44","unstructured":"Sun, J., Li, M., Chen, Z., Zhang, Y., Wang, S., Moens, M.F.: Contrast, attend and diffuse to decode high-resolution images from brain activities. In: Advances in Neural Information Processing Systems, vol. 36 (2024)"},{"key":"18_CR45","doi-asserted-by":"crossref","unstructured":"Sun, Y., Wang, Y., Liu, Z., Siegel, J., Sarma, S.: Pointgrow: autoregressively learned point cloud generation with self-attention. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 61\u201370 (2020)","DOI":"10.1109\/WACV45572.2020.9093430"},{"key":"18_CR46","doi-asserted-by":"crossref","unstructured":"Tang, J., Chen, Z., Chen, X., Wang, T., Zeng, G., Liu, Z.: LGM: large multi-view gaussian model for high-resolution 3D content creation. arXiv preprint arXiv:2402.05054 (2024)","DOI":"10.1007\/978-3-031-73235-5_1"},{"key":"18_CR47","unstructured":"Tang, J., Ren, J., Zhou, H., Liu, Z., Zeng, G.: DreamGaussian: generative Gaussian splatting for efficient 3D content creation. arXiv preprint arXiv:2309.16653 (2023)"},{"key":"18_CR48","unstructured":"Wang, P., Shi, Y.: ImageDream: image-prompt multi-view diffusion for 3D generation. arXiv preprint arXiv:2312.02201 (2023)"},{"issue":"12","key":"18_CR49","doi-asserted-by":"publisher","first-page":"4136","DOI":"10.1093\/cercor\/bhx268","volume":"28","author":"H Wen","year":"2018","unstructured":"Wen, H., Shi, J., Zhang, Y., Lu, K.H., Cao, J., Liu, Z.: Neural encoding and decoding with deep learning for dynamic natural vision. Cereb. Cortex 28(12), 4136\u20134160 (2018)","journal-title":"Cereb. Cortex"},{"key":"18_CR50","unstructured":"Xu, Q., Wang, W., Ceylan, D., Mech, R., Neumann, U.: DISN: deep implicit surface network for high-quality single-view 3D reconstruction. In: Advances in Neural Information Processing Systems, vol. 32 (2019)"},{"key":"18_CR51","unstructured":"Yang, T., Zhu, Y., Xie, Y., Zhang, A., Chen, C., Li, M.: Aim: adapting image models for efficient video action recognition. arXiv preprint arXiv:2302.03024 (2023)"},{"key":"18_CR52","unstructured":"Ye, J., et al.: Dreamreward: text-to-3D generation with human preference. arXiv preprint arXiv:2403.14613 (2024)"},{"key":"18_CR53","doi-asserted-by":"crossref","unstructured":"Zhang, R., Isola, P., Efros, A.A., Shechtman, E., Wang, O.: The unreasonable effectiveness of deep features as a perceptual metric. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00068"},{"key":"18_CR54","doi-asserted-by":"crossref","unstructured":"Zhuo, W., Ma, F., Fan, H., Yang, Y.: Vividdreamer: invariant score distillation for hyper-realistic text-to-3D generation (2024). https:\/\/arxiv.org\/abs\/2407.09822","DOI":"10.1007\/978-3-031-73223-2_8"},{"key":"18_CR55","doi-asserted-by":"crossref","unstructured":"Zhuo, W., Sun, Y., Wang, X., Zhu, L., Yang, Y.: WhitenedCSE: whitening-based contrastive learning of sentence embeddings. In: Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 12135\u201312148 (2023)","DOI":"10.18653\/v1\/2023.acl-long.677"}],"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\/978-3-031-72970-6_18","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,22]],"date-time":"2024-11-22T11:16:38Z","timestamp":1732274198000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72970-6_18"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,23]]},"ISBN":["9783031729690","9783031729706"],"references-count":55,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72970-6_18","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,23]]},"assertion":[{"value":"23 November 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"}}]}}