{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:40:35Z","timestamp":1772757635845,"version":"3.50.1"},"publisher-location":"Cham","reference-count":46,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031781711","type":"print"},{"value":"9783031781728","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T00:00:00Z","timestamp":1733184000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T00:00:00Z","timestamp":1733184000000},"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\/978-3-031-78172-8_5","type":"book-chapter","created":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T09:46:52Z","timestamp":1733132812000},"page":"63-82","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["D$$^2$$Styler: Advancing Arbitrary Style Transfer with\u00a0Discrete Diffusion Methods"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4511-1858","authenticated-orcid":false,"given":"Onkar","family":"Susladkar","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6442-0782","authenticated-orcid":false,"given":"Gayatri","family":"Deshmukh","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2908-993X","authenticated-orcid":false,"given":"Sparsh","family":"Mittal","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1581-984X","authenticated-orcid":false,"given":"Parth","family":"Shastri","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,12,3]]},"reference":[{"issue":"2","key":"5_CR1","doi-asserted-by":"publisher","first-page":"674","DOI":"10.1609\/aaai.v38i2.27824","volume":"38","author":"N Ahn","year":"2024","unstructured":"Ahn, N., et al.: DreamStyler: paint by style inversion with text-to-image diffusion models. AAAI 38(2), 674\u2013681 (2024)","journal-title":"AAAI"},{"key":"5_CR2","doi-asserted-by":"crossref","unstructured":"An, J., et\u00a0al.: ArtFlow: unbiased image style transfer via reversible neural flows. In: CVPR, pp. 862\u2013871 (2021)","DOI":"10.1109\/CVPR46437.2021.00092"},{"key":"5_CR3","unstructured":"Austin, J., et\u00a0al.: Structured denoising diffusion models in discrete state-spaces. In: NeurIPS, vol.\u00a034, pp. 17981\u201317993 (2021)"},{"key":"5_CR4","unstructured":"Chandramouli, P., Gandikota, K.V.: LDEdit: towards generalized text guided image manipulation via latent diffusion models. In: BMVC, vol.\u00a01, p.\u00a02 (2022)"},{"key":"5_CR5","unstructured":"Chang, H., et\u00a0al.: Muse: text-to-image generation via masked generative transformers. In: ICML, pp. 4055\u20134075 (2023)"},{"key":"5_CR6","doi-asserted-by":"crossref","unstructured":"Deng, Y., et\u00a0al.: StyTr2: image style transfer with transformers. In: CVPR, pp. 11326\u201311336 (2022)","DOI":"10.1109\/CVPR52688.2022.01104"},{"key":"5_CR7","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. ArXiv abs\/1810.04805 (2019)"},{"key":"5_CR8","first-page":"19822","volume":"34","author":"M Ding","year":"2021","unstructured":"Ding, M., et al.: CogView: mastering text-to-image generation via transformers. NeurIPS 34, 19822\u201319835 (2021)","journal-title":"NeurIPS"},{"key":"5_CR9","unstructured":"Dumoulin, V., Shlens, J., Kudlur, M.: A learned representation for artistic style. arXiv preprint arXiv:1610.07629 (2016)"},{"issue":"5","key":"5_CR10","doi-asserted-by":"publisher","first-page":"2338","DOI":"10.1109\/TIP.2017.2678168","volume":"26","author":"M Elad","year":"2017","unstructured":"Elad, M., Milanfar, P.: Style transfer via texture synthesis. IEEE Trans. Image Process. 26(5), 2338\u20132351 (2017)","journal-title":"IEEE Trans. Image Process."},{"key":"5_CR11","doi-asserted-by":"crossref","unstructured":"Esser, P., et\u00a0al.: Taming transformers for high-resolution image synthesis. In: CVPR, pp. 12873\u201312883 (2021)","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"5_CR12","doi-asserted-by":"crossref","unstructured":"Everaert, M.N., et\u00a0al.: Diffusion in style. In: ICCV, pp. 2251\u20132261 (2023)","DOI":"10.1109\/ICCV51070.2023.00214"},{"key":"5_CR13","unstructured":"Fan, W., Chen, J., Ma, J., Hou, J., Yi, S.: StyleFlow for content-fixed image to image translation. Arxiv (2022)"},{"key":"5_CR14","doi-asserted-by":"crossref","unstructured":"Gatys, L.A., Ecker, A.S., Bethge, M.: Image style transfer using convolutional neural networks. In: CVPR, pp. 2414\u20132423 (2016)","DOI":"10.1109\/CVPR.2016.265"},{"key":"5_CR15","unstructured":"Gu, S., et\u00a0al.: Vector quantized diffusion model for text-to-image synthesis. arXiv preprint arXiv:2111.14822 (2021)"},{"key":"5_CR16","doi-asserted-by":"crossref","unstructured":"Hamazaspyan, M., Navasardyan, S.: Diffusion-enhanced patchmatch: a framework for arbitrary style transfer with diffusion models. In: CVPR, pp. 797\u2013805 (2023)","DOI":"10.1109\/CVPRW59228.2023.00087"},{"key":"5_CR17","unstructured":"Hertz, A., et\u00a0al.: Prompt-to-prompt image editing with cross attention control. arXiv preprint arXiv:2208.01626 (2022)"},{"key":"5_CR18","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":"5_CR19","unstructured":"Hoogeboom, E., et al.: Argmax flows and multinomial diffusion: learning categorical distributions. In: NeurIPS, vol. 34, pp. 12454\u201312465 (2021)"},{"key":"5_CR20","doi-asserted-by":"crossref","unstructured":"Huang, X., Belongie, S.: Arbitrary style transfer in real-time with adaptive instance normalization. In: ICCV, pp. 1510\u20131519 (2017)","DOI":"10.1109\/ICCV.2017.167"},{"key":"5_CR21","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"694","DOI":"10.1007\/978-3-319-46475-6_43","volume-title":"Computer Vision \u2013 ECCV 2016","author":"J Johnson","year":"2016","unstructured":"Johnson, J., Alahi, A., Fei-Fei, L.: Perceptual losses for real-time style transfer and super-resolution. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9906, pp. 694\u2013711. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46475-6_43"},{"key":"5_CR22","doi-asserted-by":"crossref","unstructured":"Kim, G., et\u00a0al.: DiffusionClip: text-guided diffusion models for robust image manipulation. In: CVPR, pp. 2426\u20132435 (2022)","DOI":"10.1109\/CVPR52688.2022.00246"},{"key":"5_CR23","unstructured":"Kim, J., Kim, M., Kang, H., Lee, K.: U-GAT-IT: unsupervised generative attentional networks with adaptive layer-instance normalization for image-to-image translation. arXiv preprint arXiv:1907.10830 (2019)"},{"key":"5_CR24","unstructured":"Kingma, D.P., Welling, M.: Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114 (2013)"},{"key":"5_CR25","doi-asserted-by":"crossref","unstructured":"Kotovenko, D., Wright, M., Heimbrecht, A., Ommer, B.: Rethinking style transfer: from pixels to parameterized brushstrokes. In: CVPR, pp. 12196\u201312205 (2021)","DOI":"10.1109\/CVPR46437.2021.01202"},{"key":"5_CR26","unstructured":"Kuznetsova, A., et\u00a0al.: The open images dataset V4: unified image classification, object detection, and visual relationship detection at scale. Arxiv (2018)"},{"key":"5_CR27","unstructured":"Kwon, G., Ye, J.C.: Diffusion-based image translation using disentangled style and content representation. arXiv preprint arXiv:2209.15264 (2022)"},{"key":"5_CR28","doi-asserted-by":"crossref","unstructured":"Lee, J., et al.: Cartoon-flow: a flow-based generative adversarial network for arbitrary-style photo cartoonization. In: International Conference on Multimedia (2022)","DOI":"10.1145\/3503161.3548094"},{"key":"5_CR29","unstructured":"Li, J., et\u00a0al.: BLIP-2: bootstrapping language-image pre-training with frozen image encoders and large language models. ICML, pp. 19730\u201319742 (2023)"},{"key":"5_CR30","unstructured":"Li, Y., Fang, C., Yang, J., Wang, Z., Lu, X., Yang, M.H.: Universal style transfer via feature transforms. Adv. Neural Inf. Process. Syst. 30 (2017)"},{"key":"5_CR31","doi-asserted-by":"crossref","unstructured":"Li, Y., et\u00a0al.: Diversified texture synthesis with feed-forward networks. In: CVPR, pp. 3920\u20133928 (2017)","DOI":"10.1109\/CVPR.2017.36"},{"key":"5_CR32","doi-asserted-by":"crossref","unstructured":"Liu, S., et\u00a0al.: AdaAttN: revisit attention mechanism in arbitrary neural style transfer. In: ICCV, pp. 6649\u20136658 (2021)","DOI":"10.1109\/ICCV48922.2021.00658"},{"key":"5_CR33","unstructured":"Nichol, A.Q., Dhariwal, P.: Improved denoising diffusion probabilistic models. In: International Conference on Machine Learning, pp. 8162\u20138171. PMLR (2021)"},{"key":"5_CR34","doi-asserted-by":"crossref","unstructured":"Peebles, W., Xie, S.: Scalable diffusion models with transformers. In: ICCV, pp. 4195\u20134205 (2023)","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"5_CR35","unstructured":"Ramesh, A., et\u00a0al.: Zero-shot text-to-image generation. ICML, pp. 8821\u20138831 (2021)"},{"key":"5_CR36","doi-asserted-by":"crossref","unstructured":"Rombach, R., et\u00a0al.: High-resolution image synthesis with latent diffusion models. In: CVPR, pp. 10684\u201310695 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"5_CR37","doi-asserted-by":"crossref","unstructured":"Saharia, C., et\u00a0al.: Palette: image-to-image diffusion models. In: ACM SIGGRAPH, pp. 1\u201310 (2022)","DOI":"10.1145\/3528233.3530757"},{"key":"5_CR38","unstructured":"Saleh, B., Elgammal, A.: Large-scale classification of fine-art paintings: learning the right metric on the right feature. arXiv preprint arXiv:1505.00855 (2015)"},{"key":"5_CR39","unstructured":"Sohn, K., et\u00a0al.: StyleDrop: text-to-image synthesis of any style. NeurIPS 36 (2024)"},{"key":"5_CR40","unstructured":"Ulyanov, D., et\u00a0al.: Texture networks: feed-forward synthesis of textures and stylized images. arXiv:1603.03417 (2016)"},{"key":"5_CR41","unstructured":"Van Den\u00a0Oord, A., Vinyals, O., et\u00a0al.: Neural discrete representation learning. Adv. Neural Inf. Process. Syst. 30 (2017)"},{"key":"5_CR42","unstructured":"Vaswani, A., et\u00a0al.: Attention is all you need. In: NeurIPS, vol. 30 (2017)"},{"key":"5_CR43","doi-asserted-by":"crossref","unstructured":"Wang, Z., Zhao, L., Xing, W.: StyleDiffusion: controllable disentangled style transfer via diffusion models. In: ICCV, pp. 7677\u20137689 (2023)","DOI":"10.1109\/ICCV51070.2023.00706"},{"key":"5_CR44","doi-asserted-by":"crossref","unstructured":"Zhang, R., et\u00a0al.: Image re-composition via regional content-style decoupling. In: ACM International Conference on Multimedia, pp. 3\u201311 (2021)","DOI":"10.1145\/3474085.3475212"},{"key":"5_CR45","doi-asserted-by":"crossref","unstructured":"Zhang, Y., et\u00a0al.: Domain enhanced arbitrary image style transfer via contrastive learning. In: ACM SIGGRAPH (2022)","DOI":"10.1145\/3528233.3530736"},{"key":"5_CR46","doi-asserted-by":"crossref","unstructured":"Zhang, Y., et\u00a0al.: Inversion-based style transfer with diffusion models. In: CVPR, pp. 10146\u201310156 (2023)","DOI":"10.1109\/CVPR52729.2023.00978"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-78172-8_5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T10:03:55Z","timestamp":1733133835000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-78172-8_5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,3]]},"ISBN":["9783031781711","9783031781728"],"references-count":46,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-78172-8_5","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12,3]]},"assertion":[{"value":"3 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"}}]}}