{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T20:49:21Z","timestamp":1743108561829,"version":"3.40.3"},"publisher-location":"Cham","reference-count":61,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031733468"},{"type":"electronic","value":"9783031733475"}],"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\/978-3-031-73347-5_3","type":"book-chapter","created":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T09:15:43Z","timestamp":1730106943000},"page":"36-53","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Exploring Guided Sampling of\u00a0Conditional GANs"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-4831-883X","authenticated-orcid":false,"given":"Yifei","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8765-815X","authenticated-orcid":false,"given":"Mengfei","family":"Xia","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3801-6705","authenticated-orcid":false,"given":"Yujun","family":"Shen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9198-0304","authenticated-orcid":false,"given":"Jiapeng","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1417-1938","authenticated-orcid":false,"given":"Ceyuan","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3450-400X","authenticated-orcid":false,"given":"Kecheng","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9686-9354","authenticated-orcid":false,"given":"Lianghua","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8071-3745","authenticated-orcid":false,"given":"Yu","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4307-6334","authenticated-orcid":false,"given":"Fan","family":"Cheng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,10,29]]},"reference":[{"key":"3_CR1","doi-asserted-by":"crossref","unstructured":"Abdal, R., Qin, Y., Wonka, P.: Image2stylegan: how to embed images into the stylegan latent space? In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00453"},{"key":"3_CR2","unstructured":"Arjovsky, M., Chintala, S., Bottou, L.: Wasserstein generative adversarial networks. In: ICML (2017)"},{"key":"3_CR3","unstructured":"Betker, J., et\u00a0al.: Improving image generation with better captions. Comput. Sci. 2(3), 8 (2023). https:\/\/cdn.openai.com\/papers\/dall-e-3.pdf"},{"key":"3_CR4","unstructured":"Brock, A., Donahue, J., Simonyan, K.: Large scale gan training for high fidelity natural image synthesis. In: ICLR (2019)"},{"key":"3_CR5","doi-asserted-by":"crossref","unstructured":"Chan, E.R., et\u00a0al.: Efficient geometry-aware 3d generative adversarial networks. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01565"},{"key":"3_CR6","doi-asserted-by":"crossref","unstructured":"Chan, E.R., Monteiro, M., Kellnhofer, P., Wu, J., Wetzstein, G.: pi-gan: periodic implicit generative adversarial networks for 3d-aware image synthesis. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00574"},{"key":"3_CR7","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L., Li, K., Fei-Fei, L.: Imagenet: a large-scale hierarchical image database. In: CVPR (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"3_CR8","unstructured":"Dhariwal, P., Nichol, A.Q.: Diffusion models beat GANs on image synthesis. In: NeurIPS (2021)"},{"key":"3_CR9","unstructured":"Goodfellow, I., et al.: Generative adversarial nets. In: NeurIPS (2014)"},{"key":"3_CR10","unstructured":"Gu, J., Liu, L., Wang, P., Theobalt, C.: Stylenerf: A style-based 3d-aware generator for high-resolution image synthesis. arXiv preprint arXiv:2110.08985 (2021)"},{"key":"3_CR11","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"3_CR12","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. In: NeurIPS (2017)"},{"key":"3_CR13","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. In: NeurIPS, pp. 6840\u20136851 (2020)"},{"key":"3_CR14","unstructured":"Ho, J., Salimans, T.: Classifier-free diffusion guidance. In: Advance Neural Information Processing System Workshop (2021)"},{"key":"3_CR15","unstructured":"Ho, J., Salimans, T., Gritsenko, A., Chan, W., Norouzi, M., Fleet, D.J.: Video diffusion models. arXiv preprint arXiv:2204.03458 (2022)"},{"key":"3_CR16","unstructured":"Hu, L., Gao, X., Zhang, P., Sun, K., Zhang, B., Bo, L.: Animate anyone: Consistent and controllable image-to-video synthesis for character animation. arXiv preprint arXiv:2311.17117 (2023)"},{"key":"3_CR17","unstructured":"Huang, L., Chen, D., Liu, Y., Yujun, S., Zhao, D., Jingren, Z.: Composer: Creative and controllable image synthesis with composable conditions. arXiv preprint arxiv:2302.09778 (2023)"},{"key":"3_CR18","doi-asserted-by":"crossref","unstructured":"Isola, P., Zhu, J.Y., Zhou, T., Efros, A.A.: Image-to-image translation with conditional adversarial networks. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.632"},{"key":"3_CR19","doi-asserted-by":"crossref","unstructured":"Kang, M., et al.: Scaling up gans for text-to-image synthesis. arXiv preprint arXiv:2303.05511 (2023)","DOI":"10.1109\/CVPR52729.2023.00976"},{"key":"3_CR20","unstructured":"Karras, T., Aila, T., Laine, S., Lehtinen, J.: Progressive growing of gans for improved quality, stability, and variation. In: ICLR (2018)"},{"key":"3_CR21","unstructured":"Karras, T., Aittala, M., Aila, T., Laine, S.: Elucidating the design space of diffusion-based generative models. In: NeurIPS (2022)"},{"key":"3_CR22","unstructured":"Karras, T., et al.: Alias-free generative adversarial networks. In: NeurIPS (2021)"},{"key":"3_CR23","doi-asserted-by":"crossref","unstructured":"Karras, T., Laine, S., Aila, T.: A style-based generator architecture for generative adversarial networks. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00453"},{"key":"3_CR24","doi-asserted-by":"crossref","unstructured":"Karras, T., Laine, S., Aittala, M., Hellsten, J., Lehtinen, J., Aila, T.: Analyzing and improving the image quality of stylegan. In: CVPR, pp. 8107\u20138116 (2020)","DOI":"10.1109\/CVPR42600.2020.00813"},{"key":"3_CR25","unstructured":"Kingma, D.P., Welling, M.: Auto-encoding variational bayes. In: ICLR (2014)"},{"key":"3_CR26","unstructured":"Kynk\u00e4\u00e4nniemi, T., Karras, T., Laine, S., Lehtinen, J., Aila, T.: Improved precision and recall metric for assessing generative models. arXiv preprint arXiv:1904.06991 (2019)"},{"key":"3_CR27","doi-asserted-by":"crossref","unstructured":"Ledig, C., et\u00a0al.: Photo-realistic single image super-resolution using a generative adversarial network. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.19"},{"key":"3_CR28","doi-asserted-by":"crossref","unstructured":"Liu, Z., Luo, P., Wang, X., Tang, X.: Deep learning face attributes in the wild. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.425"},{"key":"3_CR29","unstructured":"Lu, C., Zhou, Y., Bao, F., Chen, J., Li, C., Zhu, J.: Dpm-solver: a fast ode solver for diffusion probabilistic model sampling in around 10 steps. In: NeurIPS (2022)"},{"key":"3_CR30","unstructured":"Mirza, M., Osindero, S.: Conditional generative adversarial nets. arXiv preprint arXiv:1411.1784 (2014)"},{"key":"3_CR31","doi-asserted-by":"crossref","unstructured":"Nguyen-Phuoc, T., Li, C., Theis, L., Richardt, C., Yang, Y.L.: Hologan: unsupervised learning of 3d representations from natural images. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00768"},{"key":"3_CR32","unstructured":"Van\u00a0den Oord, A., Kalchbrenner, N., Espeholt, L., Vinyals, O., Graves, A., et\u00a0al.: Conditional image generation with pixelcnn decoders. In: NeurIPS (2016)"},{"key":"3_CR33","unstructured":"Paszke, A., et\u00a0al.: Pytorch: an imperative style, high-performance deep learning library. In: NeurIPS (2019)"},{"key":"3_CR34","unstructured":"Ramesh, A., Dhariwal, P., Nichol, A., Chu, C., Chen, M.: Hierarchical text-conditional image generation with clip latents. arXiv preprint arXiv:2204.06125 (2022)"},{"key":"3_CR35","unstructured":"Rezende, D., Mohamed, S.: Variational inference with normalizing flows. In: ICML (2015)"},{"key":"3_CR36","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: CVPR (2021)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"3_CR37","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: CVPR, pp. 10684\u201310695 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"3_CR38","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":"3_CR39","doi-asserted-by":"crossref","unstructured":"Saito, M., Matsumoto, E., Saito, S.: Temporal generative adversarial nets with singular value clipping. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.308"},{"key":"3_CR40","unstructured":"Salimans, T., Ho, J.: Progressive distillation for fast sampling of diffusion models. In: ICLR (2022)"},{"key":"3_CR41","unstructured":"Sauer, A., Karras, T., Laine, S., Geiger, A., Aila, T.: Stylegan-t: Unlocking the power of gans for fast large-scale text-to-image synthesis. arXiv preprint arXiv:2301.09515 (2023)"},{"key":"3_CR42","doi-asserted-by":"crossref","unstructured":"Sauer, A., Schwarz, K., Geiger, A.: Stylegan-xl: Scaling stylegan to large diverse datasets. In: SIGGRAPH (2022)","DOI":"10.1145\/3528233.3530738"},{"key":"3_CR43","unstructured":"Schwarz, K., Liao, Y., Niemeyer, M., Geiger, A.: Graf: generative radiance fields for 3d-aware image synthesis. In: NeurIPS (2020)"},{"key":"3_CR44","doi-asserted-by":"crossref","unstructured":"Shen, Y., Gu, J., Tang, X., Zhou, B.: Interpreting the latent space of gans for semantic face editing. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00926"},{"key":"3_CR45","unstructured":"Shen, Y., Zhang, Z., Yang, D., Xu, Y., Yang, C., Zhu, J.: Hammer: An efficient toolkit for training deep models (2022). https:\/\/github.com\/bytedance\/Hammer"},{"key":"3_CR46","doi-asserted-by":"crossref","unstructured":"Shen, Y., Zhou, B.: Closed-form factorization of latent semantics in gans. In: CVPR (2020)","DOI":"10.1109\/CVPR46437.2021.00158"},{"key":"3_CR47","unstructured":"Shi, Z., Peng, S., Xu, Y., Geiger, A., Liao, Y., Shen, Y.: Deep generative models on 3d representations: A survey. arXiv preprint arXiv:2210.15663 (2022)"},{"key":"3_CR48","unstructured":"Sohl-Dickstein, J., Weiss, E., Maheswaranathan, N., Ganguli, S.: Deep unsupervised learning using nonequilibrium thermodynamics. In: ICML, pp. 2256\u20132265 (2015)"},{"key":"3_CR49","unstructured":"Song, J., Meng, C., Ermon, S.: Denoising diffusion implicit models. In: ICLR (2021)"},{"key":"3_CR50","unstructured":"Song, Y., Dhariwal, P.: Improved techniques for training consistency models. arXiv preprint arXiv:2310.14189 (2023)"},{"key":"3_CR51","unstructured":"Song, Y., Dhariwal, P., Chen, M., Sutskever, I.: Consistency models. arXiv preprint arXiv:2303.01469 (2023)"},{"key":"3_CR52","doi-asserted-by":"crossref","unstructured":"Tao, M., Bao, B.K., Tang, H., Xu, C.: Galip: Generative adversarial clips for text-to-image synthesis. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01366"},{"key":"3_CR53","doi-asserted-by":"crossref","unstructured":"Tulyakov, S., Liu, M.Y., Yang, X., Kautz, J.: Mocogan: decomposing motion and content for video generation. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00165"},{"key":"3_CR54","unstructured":"Van Den\u00a0Oord, A., Vinyals, O., et\u00a0al.: Neural discrete representation learning. In: NeurIPS (2017)"},{"key":"3_CR55","doi-asserted-by":"crossref","unstructured":"Wu, Z., Lischinski, D., Shechtman, E.: Stylespace analysis: Disentangled controls for stylegan image generation. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.01267"},{"key":"3_CR56","doi-asserted-by":"crossref","unstructured":"Xu, Y., Peng, S., Yang, C., Shen, Y., Zhou, B.: 3d-aware image synthesis via learning structural and textural representations. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01788"},{"key":"3_CR57","doi-asserted-by":"crossref","unstructured":"Yang, C., Shen, Y., Zhou, B.: Semantic hierarchy emerges in deep generative representations for scene synthesis. In: IJCV (2020)","DOI":"10.1007\/s11263-020-01429-5"},{"key":"3_CR58","doi-asserted-by":"crossref","unstructured":"Yu, J., Lin, Z., Yang, J., Shen, X., Lu, X., Huang, T.S.: Generative image inpainting with contextual attention. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00577"},{"key":"3_CR59","unstructured":"Zhang, H., Goodfellow, I., Metaxas, D., Odena, A.: Self-attention generative adversarial networks. In: ICML (2019)"},{"key":"3_CR60","doi-asserted-by":"crossref","unstructured":"Zhu, J., et al.: Linkgan: linking GAN latents to pixels for controllable image synthesis. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00704"},{"key":"3_CR61","unstructured":"Zhu, J., Yang, C., Zheng, K., Xu, Y., Shi, Z., Shen, Y.: Exploring sparse MoE in GANs for text-conditioned image synthesis. arXiv preprint arXiv:2309.03904 (2023)"}],"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\/978-3-031-73347-5_3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T09:41:38Z","timestamp":1730108498000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73347-5_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,29]]},"ISBN":["9783031733468","9783031733475"],"references-count":61,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73347-5_3","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"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"}}]}}