{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,7]],"date-time":"2025-06-07T04:03:21Z","timestamp":1749269001040,"version":"3.41.0"},"publisher-location":"Cham","reference-count":31,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031915772","type":"print"},{"value":"9783031915789","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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\/978-3-031-91578-9_5","type":"book-chapter","created":{"date-parts":[[2025,6,6]],"date-time":"2025-06-06T09:23:48Z","timestamp":1749201828000},"page":"85-100","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Conditional Hand Image Generation Using Latent Space Supervision in\u00a0Random Variable Variational Autoencoders"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8523-6749","authenticated-orcid":false,"given":"Vassilis C.","family":"Nicodemou","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9503-3723","authenticated-orcid":false,"given":"Iason","family":"Oikonomidis","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0001-3235-2735","authenticated-orcid":false,"given":"Giorgos","family":"Karvounas","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8230-3192","authenticated-orcid":false,"given":"Antonis","family":"Argyros","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,5,12]]},"reference":[{"key":"5_CR1","unstructured":"Berkhahn, F., Keys, R., Ouertani, W., Shetty, N., Gei\u00dfler, D.: Augmenting variational autoencoders with sparse labels: a unified framework for unsupervised, semi-(un) supervised, and supervised learning. arXiv preprint arXiv:1908.03015 (2019)"},{"key":"5_CR2","doi-asserted-by":"crossref","unstructured":"Chen, Z., et al.: URhand: universal relightable hands. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.00020"},{"key":"5_CR3","doi-asserted-by":"crossref","unstructured":"Zimmermann, C., Ceylan, D., Yang, J., Russell, B., Argus, M., Brox, T.: FreiHAND: a dataset for markerless capture of hand pose and shape from single RGB images. In: IEEE International Conference on Computer Vision (ICCV) (2019). https:\/\/lmb.informatik.uni-freiburg.de\/projects\/freihand\/","DOI":"10.1109\/ICCV.2019.00090"},{"key":"5_CR4","doi-asserted-by":"crossref","unstructured":"Daniel, T., Tamar, A.: Soft-introvae: analyzing and improving the introspective variational autoencoder. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4391\u20134400 (2021)","DOI":"10.1109\/CVPR46437.2021.00437"},{"key":"5_CR5","unstructured":"Dosovitskiy, A., et\u00a0al.: An image is worth 16$$\\times $$16 words: transformers for image recognition at scale. In: International Conference on Learning Representations (2020)"},{"key":"5_CR6","unstructured":"Goodfellow, I., et al.: Generative adversarial nets. In: Advances in Neural Information Processing Systems, vol. 27 (2014)"},{"key":"5_CR7","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. In: Advances in Neural Information Processing Systems, vol. 33, pp. 6840\u20136851 (2020)"},{"key":"5_CR8","doi-asserted-by":"crossref","unstructured":"Kawachi, Y., Koizumi, Y., Harada, N.: Complementary set variational autoencoder for supervised anomaly detection. In: 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 2366\u20132370. IEEE (2018)","DOI":"10.1109\/ICASSP.2018.8462181"},{"key":"5_CR9","unstructured":"Kingma, D.P., Welling, M.: Auto-encoding variational bayes. In: 2nd International Conference on Learning Representations, ICLR 2014 - Conference Track Proceedings (2014)"},{"key":"5_CR10","unstructured":"Le, L., Patterson, A., White, M.: Supervised autoencoders: improving generalization performance with unsupervised regularizers. In: Advances in Neural Information Processing Systems, vol. 31 (2018)"},{"issue":"7553","key":"5_CR11","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1038\/nature14539","volume":"521","author":"Y LeCun","year":"2015","unstructured":"LeCun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature 521(7553), 436\u2013444 (2015)","journal-title":"Nature"},{"key":"5_CR12","doi-asserted-by":"crossref","unstructured":"Lee, J., Kim, J., Kim, S.H., Choi, S.I.: Enhancing 3D hand pose estimation using SHaF: synthetic hand dataset including a forearm. Appl. Intell. 1\u201314 (2024)","DOI":"10.1007\/s10489-024-05665-x"},{"key":"5_CR13","doi-asserted-by":"crossref","unstructured":"Li, L., et al.: RenderIH: a large-scale synthetic dataset for 3D interacting hand pose estimation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 20395\u201320405 (2023)","DOI":"10.1109\/ICCV51070.2023.01865"},{"key":"5_CR14","doi-asserted-by":"crossref","unstructured":"Moon, G., Yu, S.I., Wen, H., Shiratori, T., Lee, K.M.: InterHand2.6M: a dataset and baseline for 3D interacting hand pose estimation from a single RGB image. In: European Conference on Computer Vision (ECCV) (2020)","DOI":"10.1007\/978-3-030-58565-5_33"},{"key":"5_CR15","doi-asserted-by":"crossref","unstructured":"Mueller, F., et al.: GANerated hands for real-time 3D hand tracking from monocular RGB. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 49\u201359 (2018)","DOI":"10.1109\/CVPR.2018.00013"},{"key":"5_CR16","doi-asserted-by":"crossref","unstructured":"Narasimhaswamy, S., Bhattacharya, U., Chen, X., Dasgupta, I., Mitra, S., Hoai, M.: HanDiffuser: text-to-image generation with realistic hand appearances. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2024)","DOI":"10.1109\/CVPR52733.2024.00239"},{"key":"5_CR17","doi-asserted-by":"crossref","unstructured":"Nicodemou, V.C., Oikonomidis, I., Argyros, A.: RV-VAE: integrating random variable algebra into variational autoencoders. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 196\u2013205 (2023)","DOI":"10.1109\/ICCVW60793.2023.00027"},{"key":"5_CR18","doi-asserted-by":"crossref","unstructured":"Oprea, S., et al.: H-GAN: the power of GANs in your hands. In: 2021 International joint Conference on Neural Networks (IJCNN), pp.\u00a01\u20138. IEEE (2021)","DOI":"10.1109\/IJCNN52387.2021.9534144"},{"key":"5_CR19","doi-asserted-by":"crossref","unstructured":"Parmar, G., Li, D., Lee, K., Tu, Z.: Dual contradistinctive generative autoencoder. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 823\u2013832 (2021)","DOI":"10.1109\/CVPR46437.2021.00088"},{"key":"5_CR20","unstructured":"Paszke, A., et al.: PyTorch: an imperative style, high-performance deep learning library. In: Wallach, H., Larochelle, H., Beygelzimer, A., d\u2019Alch\u00e9-Buc, F., Fox, E., Garnett, R. (eds.) Advances in Neural Information Processing Systems, vol. 32, pp. 8024\u20138035. Curran Associates, Inc. (2019)"},{"key":"5_CR21","doi-asserted-by":"crossref","unstructured":"Pavlakos, G., Shan, D., Radosavovic, I., Kanazawa, A., Fouhey, D., Malik, J.: Reconstructing hands in 3D with transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9826\u20139836 (2024)","DOI":"10.1109\/CVPR52733.2024.00938"},{"key":"5_CR22","doi-asserted-by":"crossref","unstructured":"Potamias, R.A., Ploumpis, S., Moschoglou, S., Triantafyllou, V., Zafeiriou, S.: Handy: towards a high fidelity 3D hand shape and appearance model. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4670\u20134680 (2023)","DOI":"10.1109\/CVPR52729.2023.00453"},{"key":"5_CR23","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"54","DOI":"10.1007\/978-3-030-58621-8_4","volume-title":"Computer Vision \u2013 ECCV 2020","author":"N Qian","year":"2020","unstructured":"Qian, N., Wang, J., Mueller, F., Bernard, F., Golyanik, V., Theobalt, C.: HTML: a parametric hand texture model for 3D hand reconstruction and personalization. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12356, pp. 54\u201371. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58621-8_4"},{"key":"5_CR24","unstructured":"Radford, A., Metz, L., Chintala, S.: Unsupervised representation learning with deep convolutional generative adversarial networks. arXiv preprint arXiv:1511.06434 (2015)"},{"key":"5_CR25","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":"5_CR26","unstructured":"Song, Y., Ermon, S.: Generative modeling by estimating gradients of the data distribution. In: Advances in Neural Information Processing Systems, vol. 32 (2019)"},{"key":"5_CR27","doi-asserted-by":"crossref","unstructured":"Yang, Y., Gandhi, A.N., Turk, G.: Annotated hands for generative models. arXiv preprint arXiv:2401.15075 (2024)","DOI":"10.21203\/rs.3.rs-3895352\/v1"},{"key":"5_CR28","unstructured":"Zhang, J., Jiao, J., Chen, M., Qu, L., Xu, X., Yang, Q.: 3D hand pose tracking and estimation using stereo matching. arXiv:1610.07214 (2016)"},{"key":"5_CR29","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"},{"issue":"2","key":"5_CR30","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1109\/MMUL.2012.24","volume":"19","author":"Z Zhang","year":"2012","unstructured":"Zhang, Z.: Microsoft kinect sensor and its effect. IEEE Multimed. 19(2), 4\u201310 (2012)","journal-title":"IEEE Multimed."},{"key":"5_CR31","doi-asserted-by":"crossref","unstructured":"Zhu, J.Y., Park, T., Isola, P., Efros, A.A.: Unpaired image-to-image translation using cycle-consistent adversarial networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2223\u20132232 (2017)","DOI":"10.1109\/ICCV.2017.244"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024 Workshops"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-91578-9_5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,6]],"date-time":"2025-06-06T09:23:59Z","timestamp":1749201839000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-91578-9_5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9783031915772","9783031915789"],"references-count":31,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-91578-9_5","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"12 May 2025","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"}}]}}