{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,28]],"date-time":"2025-03-28T02:32:00Z","timestamp":1743129120111,"version":"3.40.3"},"publisher-location":"Cham","reference-count":44,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031729126"},{"type":"electronic","value":"9783031729133"}],"license":[{"start":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T00:00:00Z","timestamp":1733097600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T00:00:00Z","timestamp":1733097600000},"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\/978-3-031-72913-3_16","type":"book-chapter","created":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T21:47:09Z","timestamp":1733089629000},"page":"285-301","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Enhanced Controllability of\u00a0Diffusion Models via\u00a0Feature Disentanglement and\u00a0Realism-Enhanced Sampling Methods"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0898-0341","authenticated-orcid":false,"given":"Wonwoong","family":"Cho","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3237-1899","authenticated-orcid":false,"given":"Hareesh","family":"Ravi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Midhun","family":"Harikumar","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-0368-0350","authenticated-orcid":false,"given":"Vinh","family":"Khuc","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8066-6835","authenticated-orcid":false,"given":"Krishna Kumar","family":"Singh","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3598-9918","authenticated-orcid":false,"given":"Jingwan","family":"Lu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4493-3358","authenticated-orcid":false,"given":"David","family":"Inouye","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-1057-8622","authenticated-orcid":false,"given":"Ajinkya","family":"Kale","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,12,2]]},"reference":[{"key":"16_CR1","unstructured":"Balaji, Y., et\u00a0al.: ediffi: text-to-image diffusion models with an ensemble of expert denoisers. arXiv preprint arXiv:2211.01324 (2022)"},{"key":"16_CR2","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":"16_CR3","first-page":"1877","volume":"33","author":"T Brown","year":"2020","unstructured":"Brown, T., et al.: Language models are few-shot learners. Adv. Neural. Inf. Process. Syst. 33, 1877\u20131901 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"issue":"2","key":"16_CR4","doi-asserted-by":"publisher","first-page":"131","DOI":"10.1068\/p220131","volume":"22","author":"V Bruce","year":"1993","unstructured":"Bruce, V., et al.: Sex discrimination: how do we tell the difference between male and female faces? Perception 22(2), 131\u2013152 (1993)","journal-title":"Perception"},{"key":"16_CR5","doi-asserted-by":"crossref","unstructured":"Caron, M., et al.: Emerging properties in self-supervised vision transformers. In: Proceedings of the International Conference on Computer Vision (ICCV) (2021)","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"16_CR6","doi-asserted-by":"crossref","unstructured":"Cho, W., Choi, S., Park, D.K., Shin, I., Choo, J.: Image-to-image translation via group-wise deep whitening-and-coloring transformation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10639\u201310647 (2019)","DOI":"10.1109\/CVPR.2019.01089"},{"key":"16_CR7","doi-asserted-by":"crossref","unstructured":"Choi, J., Kim, S., Jeong, Y., Gwon, Y., Yoon, S.: Ilvr: conditioning method for denoising diffusion probabilistic models. arXiv preprint arXiv:2108.02938 (2021)","DOI":"10.1109\/ICCV48922.2021.01410"},{"key":"16_CR8","doi-asserted-by":"crossref","unstructured":"Choi, J., Lee, J., Shin, C., Kim, S., Kim, H., Yoon, S.: Perception prioritized training of diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11472\u201311481 (2022)","DOI":"10.1109\/CVPR52688.2022.01118"},{"key":"16_CR9","doi-asserted-by":"crossref","unstructured":"Choi, Y., Uh, Y., Yoo, J., Ha, J.W.: Stargan v2: diverse image synthesis for multiple domains. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8188\u20138197 (2020)","DOI":"10.1109\/CVPR42600.2020.00821"},{"key":"16_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":"16_CR11","unstructured":"Gal, R., et al.: An image is worth one word: personalizing text-to-image generation using textual inversion. In: The Eleventh International Conference on Learning Representations (2023). https:\/\/openreview.net\/forum?id=NAQvF08TcyG"},{"key":"16_CR12","first-page":"9841","volume":"33","author":"E H\u00e4rk\u00f6nen","year":"2020","unstructured":"H\u00e4rk\u00f6nen, E., Hertzmann, A., Lehtinen, J., Paris, S.: Ganspace: discovering interpretable gan controls. Adv. Neural. Inf. Process. Syst. 33, 9841\u20139850 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"16_CR13","unstructured":"Hertz, A., Mokady, R., Tenenbaum, J., Aberman, K., Pritch, Y., Cohen-Or, D.: Prompt-to-prompt image editing with cross attention control. arXiv preprint arXiv:2208.01626 (2022)"},{"key":"16_CR14","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":"16_CR15","unstructured":"Ho, J., Salimans, T.: Classifier-free diffusion guidance. In: NeurIPS 2021 Workshop on Deep Generative Models and Downstream Applications (2021). https:\/\/openreview.net\/forum?id=qw8AKxfYbI"},{"key":"16_CR16","unstructured":"Ho, J., Salimans, T.: Classifier-free diffusion guidance. arXiv preprint arXiv:2207.12598 (2022)"},{"key":"16_CR17","doi-asserted-by":"crossref","unstructured":"Huang, X., Liu, M.Y., Belongie, S., Kautz, J.: Multimodal unsupervised image-to-image translation. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 172\u2013189 (2018)","DOI":"10.1007\/978-3-030-01219-9_11"},{"key":"16_CR18","doi-asserted-by":"crossref","unstructured":"Kawar, B., et al.: Imagic: text-based real image editing with diffusion models. arXiv preprint arXiv:2210.09276 (2022)","DOI":"10.1109\/CVPR52729.2023.00582"},{"key":"16_CR19","doi-asserted-by":"crossref","unstructured":"Kim, G., Kwon, T., Ye, J.C.: Diffusionclip: text-guided diffusion models for robust image manipulation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2426\u20132435 (2022)","DOI":"10.1109\/CVPR52688.2022.00246"},{"key":"16_CR20","doi-asserted-by":"crossref","unstructured":"Kwon, G., Ye, J.C.: Diagonal attention and style-based gan for content-style disentanglement in image generation and translation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 13980\u201313989 (2021)","DOI":"10.1109\/ICCV48922.2021.01372"},{"key":"16_CR21","unstructured":"Kwon, G., Ye, J.C.: Diffusion-based image translation using disentangled style and content representation. arXiv preprint arXiv:2209.15264 (2022)"},{"key":"16_CR22","doi-asserted-by":"crossref","unstructured":"Lee, H.Y., Tseng, H.Y., Huang, J.B., Singh, M., Yang, M.H.: Diverse image-to-image translation via disentangled representations. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 35\u201351 (2018)","DOI":"10.1007\/978-3-030-01246-5_3"},{"key":"16_CR23","unstructured":"Liew, J.H., Yan, H., Zhou, D., Feng, J.: Magicmix: semantic mixing with diffusion models. arXiv preprint arXiv:2210.16056 (2022)"},{"key":"16_CR24","doi-asserted-by":"crossref","unstructured":"Liu, N., Li, S., Du, Y., Torralba, A., Tenenbaum, J.B.: Compositional visual generation with composable diffusion models. In: Proceedings of the European Conference on Computer Vision (ECCV) (2022)","DOI":"10.1007\/978-3-031-19790-1_26"},{"key":"16_CR25","unstructured":"Meng, C., et al.: Sdedit: guided image synthesis and editing with stochastic differential equations. In: International Conference on Learning Representations (2021)"},{"key":"16_CR26","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":"16_CR27","unstructured":"Nichol, A.Q., Dhariwal, P.: Improved denoising diffusion probabilistic models. In: International Conference on Machine Learning, pp. 8162\u20138171. PMLR (2021)"},{"key":"16_CR28","first-page":"7198","volume":"33","author":"T Park","year":"2020","unstructured":"Park, T., et al.: Swapping autoencoder for deep image manipulation. Adv. Neural. Inf. Process. Syst. 33, 7198\u20137211 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"16_CR29","doi-asserted-by":"crossref","unstructured":"Preechakul, K., Chatthee, N., Wizadwongsa, S., Suwajanakorn, S.: Diffusion autoencoders: toward a meaningful and decodable representation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10619\u201310629 (2022)","DOI":"10.1109\/CVPR52688.2022.01036"},{"key":"16_CR30","doi-asserted-by":"crossref","unstructured":"Qi, T., et al.: Deadiff: an efficient stylization diffusion model with disentangled representations. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8693\u20138702 (2024)","DOI":"10.1109\/CVPR52733.2024.00830"},{"key":"16_CR31","doi-asserted-by":"publisher","unstructured":"Ramesh, A., Dhariwal, P., Nichol, A., Chu, C., Chen, M.: Hierarchical text-conditional image generation with clip latents (2022). https:\/\/doi.org\/10.48550\/ARXIV.2204.06125. https:\/\/arxiv.org\/abs\/2204.06125","DOI":"10.48550\/ARXIV.2204.06125"},{"key":"16_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":"16_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":"16_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 (2023)","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"16_CR35","doi-asserted-by":"publisher","unstructured":"Saharia, C., et al.: Photorealistic text-to-image diffusion models with deep language understanding (2022). https:\/\/doi.org\/10.48550\/ARXIV.2205.11487. https:\/\/arxiv.org\/abs\/2205.11487","DOI":"10.48550\/ARXIV.2205.11487"},{"key":"16_CR36","unstructured":"Sohl-Dickstein, J., Weiss, E., Maheswaranathan, N., Ganguli, S.: Deep unsupervised learning using nonequilibrium thermodynamics. In: International Conference on Machine Learning, pp. 2256\u20132265. PMLR (2015)"},{"key":"16_CR37","unstructured":"Song, J., Meng, C., Ermon, S.: Denoising diffusion implicit models. In: International Conference on Learning Representations (2020)"},{"key":"16_CR38","unstructured":"Song, Y., Sohl-Dickstein, J., Kingma, D.P., Kumar, A., Ermon, S., Poole, B.: Score-based generative modeling through stochastic differential equations. In: International Conference on Learning Representations (2021). https:\/\/openreview.net\/forum?id=PxTIG12RRHS"},{"key":"16_CR39","doi-asserted-by":"crossref","unstructured":"Tumanyan, N., Bar-Tal, O., Bagon, S., Dekel, T.: Splicing vit features for semantic appearance transfer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10748\u201310757 (2022)","DOI":"10.1109\/CVPR52688.2022.01048"},{"key":"16_CR40","doi-asserted-by":"crossref","unstructured":"Valevski, D., Kalman, M., Matias, Y., Leviathan, Y.: Unitune: text-driven image editing by fine tuning an image generation model on a single image. arXiv preprint arXiv:2210.09477 (2022)","DOI":"10.1145\/3592451"},{"issue":"7","key":"16_CR41","doi-asserted-by":"publisher","first-page":"1661","DOI":"10.1162\/NECO_a_00142","volume":"23","author":"P Vincent","year":"2011","unstructured":"Vincent, P.: A connection between score matching and denoising autoencoders. Neural Comput. 23(7), 1661\u20131674 (2011). https:\/\/doi.org\/10.1162\/NECO_a_00142","journal-title":"Neural Comput."},{"key":"16_CR42","unstructured":"Yang, T., Wang, Y., Lu, Y., Zheng, N.: Disdiff: unsupervised disentanglement of diffusion probabilistic models. In: NeurIPS (2023)"},{"key":"16_CR43","doi-asserted-by":"publisher","unstructured":"Yu, J., et al.: Scaling autoregressive models for content-rich text-to-image generation (2022). https:\/\/doi.org\/10.48550\/ARXIV.2206.10789. https:\/\/arxiv.org\/abs\/2206.10789","DOI":"10.48550\/ARXIV.2206.10789"},{"key":"16_CR44","doi-asserted-by":"crossref","unstructured":"Zhang, L., Agrawala, M.: Adding conditional control to text-to-image diffusion models. arXiv preprint arXiv:2302.05543 (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\/978-3-031-72913-3_16","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T23:24:59Z","timestamp":1733095499000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72913-3_16"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,2]]},"ISBN":["9783031729126","9783031729133"],"references-count":44,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72913-3_16","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,12,2]]},"assertion":[{"value":"2 December 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"}}]}}