{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,28]],"date-time":"2025-08-28T12:54:31Z","timestamp":1756385671000,"version":"3.40.3"},"publisher-location":"Cham","reference-count":42,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031783883"},{"type":"electronic","value":"9783031783890"}],"license":[{"start":{"date-parts":[[2024,12,5]],"date-time":"2024-12-05T00:00:00Z","timestamp":1733356800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,5]],"date-time":"2024-12-05T00:00:00Z","timestamp":1733356800000},"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\/978-3-031-78389-0_26","type":"book-chapter","created":{"date-parts":[[2024,12,4]],"date-time":"2024-12-04T14:17:42Z","timestamp":1733321862000},"page":"386-400","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["LDFaceNet: Latent Diffusion-Based Network for High-Fidelity Deepfake Generation"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-1995-9841","authenticated-orcid":false,"given":"Dwij","family":"Mehta","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-6728-6677","authenticated-orcid":false,"given":"Aditya","family":"Mehta","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1865-3512","authenticated-orcid":false,"given":"Pratik","family":"Narang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,12,5]]},"reference":[{"key":"26_CR1","doi-asserted-by":"crossref","unstructured":"Blanz, V., Scherbaum, K., Vetter, T., Seidel, H.P.: Exchanging faces in images. In: Computer Graphics Forum. vol.\u00a023, pp. 669\u2013676. Wiley Online Library (2004)","DOI":"10.1111\/j.1467-8659.2004.00799.x"},{"key":"26_CR2","unstructured":"Brock, A., Donahue, J., Simonyan, K.: Large scale gan training for high fidelity natural image synthesis. arXiv preprint arXiv:1809.11096 (2018)"},{"key":"26_CR3","doi-asserted-by":"crossref","unstructured":"Burt, P.J., Adelson, E.H.: The laplacian pyramid as a compact image code. In: Readings in computer vision, pp. 671\u2013679. Elsevier (1987)","DOI":"10.1016\/B978-0-08-051581-6.50065-9"},{"key":"26_CR4","doi-asserted-by":"crossref","unstructured":"Cao, Q., Shen, L., Xie, W., Parkhi, O.M., Zisserman, A.: Vggface2: A dataset for recognising faces across pose and age. In: 2018 13th IEEE international conference on automatic face & gesture recognition (FG 2018). pp. 67\u201374. IEEE (2018)","DOI":"10.1109\/FG.2018.00020"},{"key":"26_CR5","doi-asserted-by":"crossref","unstructured":"Chen, R., Chen, X., Ni, B., Ge, Y.: Simswap: An efficient framework for high fidelity face swapping. In: Proceedings of the 28th ACM International Conference on Multimedia. pp. 2003\u20132011 (2020)","DOI":"10.1145\/3394171.3413630"},{"key":"26_CR6","unstructured":"Child, R., Gray, S., Radford, A., Sutskever, I.: Generating long sequences with sparse transformers. arXiv preprint arXiv:1904.10509 (2019)"},{"key":"26_CR7","unstructured":"Deepfakes: Deepfakes\/faceswap: Deepfakes software for all (2021), https:\/\/github.com\/deepfakes\/faceswap"},{"key":"26_CR8","doi-asserted-by":"crossref","unstructured":"Deng, J., Guo, J., Xue, N., Zafeiriou, S.: Arcface: Additive angular margin loss for deep face recognition. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. pp. 4690\u20134699 (2019)","DOI":"10.1109\/CVPR.2019.00482"},{"key":"26_CR9","doi-asserted-by":"crossref","unstructured":"Deng, Y., Yang, J., Xu, S., Chen, D., Jia, Y., Tong, X.: Accurate 3d face reconstruction with weakly-supervised learning: From single image to image set. In: IEEE Computer Vision and Pattern Recognition Workshops (2019)","DOI":"10.1109\/CVPRW.2019.00038"},{"key":"26_CR10","first-page":"8780","volume":"34","author":"P Dhariwal","year":"2021","unstructured":"Dhariwal, P., Nichol, A.: Diffusion models beat gans on image synthesis. Adv. Neural. Inf. Process. Syst. 34, 8780\u20138794 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"26_CR11","doi-asserted-by":"crossref","unstructured":"Esser, P., Rombach, R., Ommer, B.: Taming transformers for high-resolution image synthesis. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. pp. 12873\u201312883 (2021)","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"26_CR12","unstructured":"Goodfellow, I.J., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., Bengio, Y.: Generative adversarial networks (2014)"},{"key":"26_CR13","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition. pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"26_CR14","unstructured":"Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B., Hochreiter, S.: Gans trained by a two time-scale update rule converge to a local nash equilibrium. Advances in neural information processing systems 30 (2017)"},{"key":"26_CR15","first-page":"6840","volume":"33","author":"J Ho","year":"2020","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. Adv. Neural. Inf. Process. Syst. 33, 6840\u20136851 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"26_CR16","unstructured":"Ho, J., Salimans, T.: Classifier-free diffusion guidance. arXiv preprint arXiv:2207.12598 (2022)"},{"key":"26_CR17","doi-asserted-by":"crossref","unstructured":"Jiang, L., Li, R., Wu, W., Qian, C., Loy, C.C.: Deeperforensics-1.0: A large-scale dataset for real-world face forgery detection. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. pp. 2889\u20132898 (2020)","DOI":"10.1109\/CVPR42600.2020.00296"},{"key":"26_CR18","unstructured":"Kalchbrenner, N., Elsen, E., Simonyan, K., Noury, S., Casagrande, N., Lockhart, E., Stimberg, F., van\u00a0den Oord, A., Dieleman, S., Kavukcuoglu, K.: Efficient neural audio synthesis. In: Dy, J., Krause, A. (eds.) Proceedings of the 35th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol.\u00a080, pp. 2410\u20132419. PMLR (10\u201315 Jul 2018), https:\/\/proceedings.mlr.press\/v80\/kalchbrenner18a.html"},{"key":"26_CR19","unstructured":"Karras, T., Aila, T., Laine, S., Lehtinen, J.: Progressive growing of gans for improved quality, stability, and variation (2018)"},{"key":"26_CR20","unstructured":"Kim, K., Kim, Y., Cho, S., Seo, J., Nam, J., Lee, K., Kim, S., Lee, K.: Diffface: Diffusion-based face swapping with facial guidance. arXiv preprint arXiv:2212.13344 (2022)"},{"key":"26_CR21","doi-asserted-by":"crossref","unstructured":"Li, Y., Ma, C., Yan, Y., Zhu, W., Yang, X.: 3d-aware face swapping. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). pp. 12705\u201312714 (June 2023)","DOI":"10.1109\/CVPR52729.2023.01222"},{"key":"26_CR22","doi-asserted-by":"crossref","unstructured":"Liu, Z., Li, M., Zhang, Y., Wang, C., Zhang, Q., Wang, J., Nie, Y.: Fine-grained face swapping via regional gan inversion. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. pp. 8578\u20138587 (2023)","DOI":"10.1109\/CVPR52729.2023.00829"},{"key":"26_CR23","unstructured":"Liu, Z., Luo, P., Wang, X., Tang, X.: Large-scale celebfaces attributes (celeba) dataset. Retrieved August 15(2018), 11 (2018)"},{"key":"26_CR24","unstructured":"Nichol, A.Q., Dhariwal, P.: Improved denoising diffusion probabilistic models. In: International Conference on Machine Learning. pp. 8162\u20138171. PMLR (2021)"},{"key":"26_CR25","doi-asserted-by":"crossref","unstructured":"Nirkin, Y., Masi, I., Tuan, A.T., Hassner, T., Medioni, G.: On face segmentation, face swapping, and face perception. In: 2018 13th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2018). pp. 98\u2013105. IEEE (2018)","DOI":"10.1109\/FG.2018.00024"},{"key":"26_CR26","doi-asserted-by":"publisher","unstructured":"Prenger, R., Valle, R., Catanzaro, B.: Waveglow: A flow-based generative network for speech synthesis. In: ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). pp. 3617\u20133621 (2019). https:\/\/doi.org\/10.1109\/ICASSP.2019.8683143","DOI":"10.1109\/ICASSP.2019.8683143"},{"key":"26_CR27","unstructured":"Razavi, A., van\u00a0den Oord, A., Vinyals, O.: Generating diverse high-fidelity images with vq-vae-2. In: Wallach, H., Larochelle, H., Beygelzimer, A., d\u2019 Alch\u00e9-Buc, F., Fox, E., Garnett, R. (eds.) Advances in Neural Information Processing Systems. vol.\u00a032. Curran Associates, Inc. (2019), https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2019\/file\/5f8e2fa1718d1bbcadf1cd9c7a54fb8c-Paper.pdf"},{"key":"26_CR28","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":"26_CR29","doi-asserted-by":"crossref","unstructured":"Ruiz, N., Chong, E., Rehg, J.M.: Fine-grained head pose estimation without keypoints. In: Proceedings of the IEEE conference on computer vision and pattern recognition workshops. pp. 2074\u20132083 (2018)","DOI":"10.1109\/CVPRW.2018.00281"},{"key":"26_CR30","unstructured":"Salimans, T., Goodfellow, I., Zaremba, W., Cheung, V., Radford, A., Chen, X.: Improved techniques for training gans. Advances in neural information processing systems 29 (2016)"},{"key":"26_CR31","doi-asserted-by":"crossref","unstructured":"Schroff, F., Kalenichenko, D., Philbin, J.: Facenet: A unified embedding for face recognition and clustering. In: Proceedings of the IEEE conference on computer vision and pattern recognition. pp. 815\u2013823 (2015)","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"26_CR32","unstructured":"Song, J., Meng, C., Ermon, S.: Denoising diffusion implicit models. arXiv preprint arXiv:2010.02502 (2020)"},{"key":"26_CR33","unstructured":"Song, Y., Ermon, S.: Generative modeling by estimating gradients of the data distribution. In: Wallach, H., Larochelle, H., Beygelzimer, A., d\u2019 Alch\u00e9-Buc, F., Fox, E., Garnett, R. (eds.) Advances in Neural Information Processing Systems. vol.\u00a032. Curran Associates, Inc. (2019), https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2019\/file\/3001ef257407d5a371a96dcd947c7d93-Paper.pdf"},{"key":"26_CR34","unstructured":"Sun, Y., Chen, Y., Wang, X., Tang, X.: Deep learning face representation by joint identification-verification. Advances in neural information processing systems 27 (2014)"},{"key":"26_CR35","doi-asserted-by":"crossref","unstructured":"Taigman, Y., Yang, M., Ranzato, M., Wolf, L.: Deepface: Closing the gap to human-level performance in face verification. In: Proceedings of the IEEE conference on computer vision and pattern recognition. pp. 1701\u20131708 (2014)","DOI":"10.1109\/CVPR.2014.220"},{"key":"26_CR36","first-page":"19667","volume":"33","author":"A Vahdat","year":"2020","unstructured":"Vahdat, A., Kautz, J.: Nvae: A deep hierarchical variational autoencoder. Adv. Neural. Inf. Process. Syst. 33, 19667\u201319679 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"26_CR37","first-page":"11287","volume":"34","author":"A Vahdat","year":"2021","unstructured":"Vahdat, A., Kreis, K., Kautz, J.: Score-based generative modeling in latent space. Adv. Neural. Inf. Process. Syst. 34, 11287\u201311302 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"26_CR38","unstructured":"Van Den\u00a0Oord, A., Kalchbrenner, N., Kavukcuoglu, K.: Pixel recurrent neural networks. In: International conference on machine learning. pp. 1747\u20131756. PMLR (2016)"},{"key":"26_CR39","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, \u0141., Polosukhin, I.: Attention is all you need. Advances in neural information processing systems 30 (2017)"},{"key":"26_CR40","doi-asserted-by":"crossref","unstructured":"Xu, Z., Hong, Z., Ding, C., Zhu, Z., Han, J., Liu, J., Ding, E.: Mobilefaceswap: A lightweight framework for video face swapping. In: Proceedings of the AAAI Conference on Artificial Intelligence. vol.\u00a036, pp. 2973\u20132981 (2022)","DOI":"10.1609\/aaai.v36i3.20203"},{"key":"26_CR41","doi-asserted-by":"crossref","unstructured":"Yu, C., Wang, J., Peng, C., Gao, C., Yu, G., Sang, N.: Bisenet: Bilateral segmentation network for real-time semantic segmentation. In: Proceedings of the European conference on computer vision (ECCV). pp. 325\u2013341 (2018)","DOI":"10.1007\/978-3-030-01261-8_20"},{"key":"26_CR42","doi-asserted-by":"crossref","unstructured":"Zhu, Y., Li, Q., Wang, J., Xu, C.Z., Sun, Z.: One shot face swapping on megapixels. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. pp. 4834\u20134844 (2021)","DOI":"10.1109\/CVPR46437.2021.00480"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-78389-0_26","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,4]],"date-time":"2024-12-04T15:09:16Z","timestamp":1733324956000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-78389-0_26"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,5]]},"ISBN":["9783031783883","9783031783890"],"references-count":42,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-78389-0_26","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,12,5]]},"assertion":[{"value":"5 December 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICPR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Pattern Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Kolkata","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"India","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":"1 December 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 December 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icpr2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/icpr2024.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}