{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T11:41:23Z","timestamp":1776858083940,"version":"3.51.2"},"publisher-location":"Singapore","reference-count":39,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819658114","type":"print"},{"value":"9789819658121","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\/978-981-96-5812-1_14","type":"book-chapter","created":{"date-parts":[[2025,4,25]],"date-time":"2025-04-25T18:44:34Z","timestamp":1745606674000},"page":"253-270","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Sketch-Guided Scene-Level Image Editing with\u00a0Diffusion Models"],"prefix":"10.1007","author":[{"given":"Ran","family":"Zuo","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haoxiang","family":"Hu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoming","family":"Deng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yaokun","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu-Kun","family":"Lai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cuixia","family":"Ma","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yong-Jin","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongan","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,4,26]]},"reference":[{"key":"14_CR1","unstructured":"https:\/\/github.com\/mikonvergence\/ControlNetInpaint"},{"key":"14_CR2","doi-asserted-by":"crossref","unstructured":"Bashkirova, D., Lezama, J., Sohn, K., Saenko, K., Essa, I.: Masksketch: unpaired structure-guided masked image generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1879\u20131889 (2023)","DOI":"10.1109\/CVPR52729.2023.00187"},{"key":"14_CR3","doi-asserted-by":"crossref","unstructured":"Chen, S.Y., et al.: Deepfaceediting: deep face generation and editing with disentangled geometry and appearance control. arXiv preprint arXiv:2105.08935 (2021)","DOI":"10.1145\/3476576.3476648"},{"key":"14_CR4","doi-asserted-by":"crossref","unstructured":"Cheng, S.I., Chen, Y.J., Chiu, W.C., Tseng, H.Y., Lee, H.Y.: Adaptively-realistic image generation from stroke and sketch with diffusion model. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 4054\u20134062 (2023)","DOI":"10.1109\/WACV56688.2023.00404"},{"key":"14_CR5","unstructured":"Goodfellow, I., et al.: Generative adversarial nets. In: Advances in Neural Information Processing Systems, vol. 27 (2014)"},{"key":"14_CR6","doi-asserted-by":"crossref","unstructured":"Gu, S., Bao, J., Chen, D., Wen, F.: Giqa: generated image quality assessment. In: Proceedings of the IEEE\/CVF European Conference on Computer Vision, pp. 369\u2013385. Springer (2020)","DOI":"10.1007\/978-3-030-58621-8_22"},{"key":"14_CR7","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask r-cnn. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 2961\u20132969 (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"14_CR8","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: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"14_CR9","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":"14_CR10","doi-asserted-by":"crossref","unstructured":"Isola, P., Zhu, J.Y., Zhou, T., Efros, A.A.: Image-to-image translation with conditional adversarial networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1125\u20131134 (2017)","DOI":"10.1109\/CVPR.2017.632"},{"key":"14_CR11","doi-asserted-by":"crossref","unstructured":"Jo, Y., Park, J.: Sc-fegan: face editing generative adversarial network with user\u2019s sketch and color. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 1745\u20131753 (2019)","DOI":"10.1109\/ICCV.2019.00183"},{"key":"14_CR12","doi-asserted-by":"crossref","unstructured":"Kawar, B., et al.: Imagic: text-based real image editing with diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6007\u20136017 (2023)","DOI":"10.1109\/CVPR52729.2023.00582"},{"key":"14_CR13","unstructured":"Li, Y., et al.: Snapfusion: text-to-image diffusion model on mobile devices within two seconds. In: Advances in Neural Information Processing Systems, vol. 36 (2024)"},{"key":"14_CR14","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., et al.: Microsoft coco: common objects in context. In: Proceedings of the IEEE\/CVF European Conference on Computer Vision, pp. 740\u2013755. Springer (2014)","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"14_CR15","doi-asserted-by":"crossref","unstructured":"Liu, H., et al.: Deflocnet: deep image editing via flexible low-level controls. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10765\u201310774 (2021)","DOI":"10.1109\/CVPR46437.2021.01062"},{"key":"14_CR16","unstructured":"MaungMaung, A., Shing, M., Mitsui, K., Sawada, K., Okura, F.: Text-guided scene sketch-to-photo synthesis. arXiv preprint arXiv:2302.06883 (2023)"},{"key":"14_CR17","doi-asserted-by":"crossref","unstructured":"Mo, S., et al.: Freecontrol: training-free spatial control of any text-to-image diffusion model with any condition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7465\u20137475 (2024)","DOI":"10.1109\/CVPR52733.2024.00713"},{"key":"14_CR18","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":"14_CR19","unstructured":"Peng, Y., Zhao, C., Xie, H., Fukusato, T., Miyata, K.: Difffacesketch: high-fidelity face image synthesis with sketch-guided latent diffusion model. arXiv preprint arXiv:2302.06908 (2023)"},{"key":"14_CR20","doi-asserted-by":"crossref","unstructured":"Portenier, T., Hu, Q., Szabo, A., Bigdeli, S.A., Favaro, P., Zwicker, M.: Faceshop: deep sketch-based face image editing. arXiv preprint arXiv:1804.08972 (2018)","DOI":"10.1145\/3197517.3201393"},{"key":"14_CR21","unstructured":"Qin, C., et\u00a0al.: Unicontrol: a unified diffusion model for controllable visual generation in the wild. arXiv preprint arXiv:2305.11147 (2023)"},{"key":"14_CR22","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 8748\u20138763. PMLR (2021)"},{"key":"14_CR23","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":"14_CR24","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":"14_CR25","unstructured":"Song, J., Meng, C., Ermon, S.: Denoising diffusion implicit models. arXiv preprint arXiv:2010.02502 (2020)"},{"key":"14_CR26","doi-asserted-by":"crossref","unstructured":"Su, Z., et al.: Pixel difference networks for efficient edge detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 5117\u20135127 (2021)","DOI":"10.1109\/ICCV48922.2021.00507"},{"key":"14_CR27","unstructured":"Tang, Z., Yang, Z., Zhu, C., Zeng, M., Bansal, M.: Any-to-any generation via composable diffusion. In: Advances in Neural Information Processing Systems, vol. 36 (2024)"},{"key":"14_CR28","doi-asserted-by":"crossref","unstructured":"Tumanyan, N., Geyer, M., Bagon, S., Dekel, T.: Plug-and-play diffusion features for text-driven image-to-image translation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1921\u20131930 (2023)","DOI":"10.1109\/CVPR52729.2023.00191"},{"issue":"4","key":"14_CR29","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3528223.3530068","volume":"41","author":"Y Vinker","year":"2022","unstructured":"Vinker, Y., et al.: Clipasso: semantically-aware object sketching. ACM Trans. Graph. 41(4), 1\u201311 (2022)","journal-title":"ACM Trans. Graph."},{"key":"14_CR30","doi-asserted-by":"crossref","unstructured":"Voynov, A., Aberman, K., Cohen-Or, D.: Sketch-guided text-to-image diffusion models. arXiv preprint arXiv:2211.13752 (2022)","DOI":"10.1145\/3588432.3591560"},{"key":"14_CR31","unstructured":"Wang, Q., Kong, D., Lin, F., Qi, Y.: Diffsketching: sketch control image synthesis with diffusion models. arXiv preprint arXiv:2305.18812 (2023)"},{"key":"14_CR32","doi-asserted-by":"crossref","unstructured":"Wang, T.C., Liu, M.Y., Zhu, J.Y., Tao, A., Kautz, J., Catanzaro, B.: High-resolution image synthesis and semantic manipulation with conditional gans. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8798\u20138807 (2018)","DOI":"10.1109\/CVPR.2018.00917"},{"key":"14_CR33","doi-asserted-by":"crossref","unstructured":"Xue, H., Huang, Z., Sun, Q., Song, L., Zhang, W.: Freestyle layout-to-image synthesis. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14256\u201314266 (2023)","DOI":"10.1109\/CVPR52729.2023.01370"},{"key":"14_CR34","doi-asserted-by":"crossref","unstructured":"Yang, B., et al.: Paint by example: exemplar-based image editing with diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18381\u201318391 (2023)","DOI":"10.1109\/CVPR52729.2023.01763"},{"key":"14_CR35","doi-asserted-by":"crossref","unstructured":"Yang, S., Wang, Z., Liu, J., Guo, Z.: Deep plastic surgery: robust and controllable image editing with human-drawn sketches. In: Proceedings of the IEEE\/CVF European Conference on Computer Vision, pp. 601\u2013617. Springer (2020)","DOI":"10.1007\/978-3-030-58555-6_36"},{"key":"14_CR36","doi-asserted-by":"crossref","unstructured":"Yu, J., Lin, Z., Yang, J., Shen, X., Lu, X., Huang, T.S.: Free-form image inpainting with gated convolution. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4471\u20134480 (2019)","DOI":"10.1109\/ICCV.2019.00457"},{"key":"14_CR37","doi-asserted-by":"crossref","unstructured":"Zeng, Y., Lin, Z., Patel, V.M.: Sketchedit: mask-free local image manipulation with partial sketches. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5951\u20135961 (2022)","DOI":"10.1109\/CVPR52688.2022.00586"},{"key":"14_CR38","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"},{"key":"14_CR39","unstructured":"Zhang, Z., et al.: Stroke-based semantic segmentation for scene-level free-hand sketches. The Visual Computer, pp. 1\u201313 (2022)"}],"container-title":["Lecture Notes in Computer Science","Computational Visual Media"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-5812-1_14","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,25]],"date-time":"2025-04-25T18:44:54Z","timestamp":1745606694000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-5812-1_14"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819658114","9789819658121"],"references-count":39,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-5812-1_14","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":"26 April 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"CVM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Computational Visual Media","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Hong Kong SAR","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19 April 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21 April 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"cvm2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/iccvm.org\/2025\/index.htm","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}