{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,21]],"date-time":"2026-01-21T11:19:20Z","timestamp":1768994360494,"version":"3.49.0"},"publisher-location":"Singapore","reference-count":38,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819556922","type":"print"},{"value":"9789819556939","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":[[2026]]},"DOI":"10.1007\/978-981-95-5693-9_16","type":"book-chapter","created":{"date-parts":[[2026,1,20]],"date-time":"2026-01-20T21:22:28Z","timestamp":1768944148000},"page":"225-239","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["SketchMaster: From Rough Lines to\u00a0Photorealistic Scenes with\u00a0Adaptive Guidance"],"prefix":"10.1007","author":[{"given":"Zhifeng","family":"Xie","sequence":"first","affiliation":[]},{"given":"Shiyu","family":"Xia","sequence":"additional","affiliation":[]},{"given":"Bolun","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Xiaoming","family":"He","sequence":"additional","affiliation":[]},{"given":"Mengtian","family":"Li","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2026,1,21]]},"reference":[{"key":"16_CR1","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":"16_CR2","doi-asserted-by":"crossref","unstructured":"Caesar, H., Uijlings, J., Ferrari, V.: Coco-stuff: Thing and stuff classes in context. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1209\u20131218 (2018)","DOI":"10.1109\/CVPR.2018.00132"},{"key":"16_CR3","doi-asserted-by":"crossref","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. In: European Conference on Computer Vision, pp. 213\u2013229. Springer (2020)","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"16_CR4","doi-asserted-by":"crossref","unstructured":"Chan, C., Durand, F., Isola, P.: Learning to generate line drawings that convey geometry and semantics. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7915\u20137925 (2022)","DOI":"10.1109\/CVPR52688.2022.00776"},{"key":"16_CR5","doi-asserted-by":"crossref","unstructured":"Chen, D.Y., Bhunia, A.K., Koley, S., Sain, A., Chowdhury, P.N., Song, Y.Z.: Democaricature: Democratising caricature generation with a rough sketch. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8629\u20138639 (2024)","DOI":"10.1109\/CVPR52733.2024.00824"},{"key":"16_CR6","doi-asserted-by":"crossref","unstructured":"Chen, M., Laina, I., Vedaldi, A.: Training-free layout control with cross-attention guidance. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 5343\u20135353 (2024)","DOI":"10.1109\/WACV57701.2024.00526"},{"key":"16_CR7","doi-asserted-by":"crossref","unstructured":"Chen, W., Hays, J.: Sketchygan: towards diverse and realistic sketch to image synthesis. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 9416\u20139425 (2018)","DOI":"10.1109\/CVPR.2018.00981"},{"key":"16_CR8","doi-asserted-by":"crossref","unstructured":"Cheng, Z., Wu, L., Wang, C., Meng, X.: Scene sketch-to-image synthesis based on multi-object control. In: ICASSP 2024-2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 3775\u20133779. IEEE (2024)","DOI":"10.1109\/ICASSP48485.2024.10446608"},{"key":"16_CR9","doi-asserted-by":"crossref","unstructured":"Chowdhury, P.N., Sain, A., Bhunia, A.K., Xiang, T., Gryaditskaya, Y., Song, Y.Z.: Fs-coco: towards understanding of freehand sketches of common objects in context. In: European Conference on Computer Vision, pp. 253\u2013270. Springer (2022)","DOI":"10.1007\/978-3-031-20074-8_15"},{"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","doi-asserted-by":"crossref","unstructured":"Gao, C., Liu, Q., Xu, Q., Wang, L., Liu, J., Zou, C.: Sketchycoco: image generation from freehand scene sketches. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5174\u20135183 (2020)","DOI":"10.1109\/CVPR42600.2020.00522"},{"key":"16_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. Advances in neural information processing systems 30 (2017)"},{"key":"16_CR13","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_CR14","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 Conference on Computer Vision and Pattern Recognition, pp. 1125\u20131134 (2017)","DOI":"10.1109\/CVPR.2017.632"},{"key":"16_CR15","unstructured":"Kingma, D.P.: Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114 (2013)"},{"key":"16_CR16","doi-asserted-by":"crossref","unstructured":"Koley, S., Bhunia, A.K., Sain, A., Chowdhury, P.N., Xiang, T., Song, Y.Z.: Picture that sketch: Photorealistic image generation from abstract sketches. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6850\u20136861 (2023)","DOI":"10.1109\/CVPR52729.2023.00662"},{"key":"16_CR17","doi-asserted-by":"crossref","unstructured":"Koley, S., et al.: It\u2019s all about your sketch: Democratising sketch control in diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7204\u20137214 (2024)","DOI":"10.1109\/CVPR52733.2024.00688"},{"key":"16_CR18","doi-asserted-by":"crossref","unstructured":"Li, M., Lin, Z., Mech, R., Yumer, E., Ramanan, D.: Photo-sketching: inferring contour drawings from images. In: 2019 IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 1403\u20131412. IEEE (2019)","DOI":"10.1109\/WACV.2019.00154"},{"key":"16_CR19","doi-asserted-by":"crossref","unstructured":"Li, Y., Liu, H., Wu, Q., Mu, F., Yang, J., Gao, J., Li, C., Lee, Y.J.: Gligen: open-set grounded text-to-image generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 22511\u201322521 (2023)","DOI":"10.1109\/CVPR52729.2023.02156"},{"key":"16_CR20","unstructured":"Lin, K.H., Mo, S., Klingher, B., Mu, F., Zhou, B.: Ctrl-x: Controlling structure and appearance for text-to-image generation without guidance. arXiv preprint arXiv:2406.07540 (2024)"},{"key":"16_CR21","unstructured":"Loshchilov, I.: Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)"},{"key":"16_CR22","doi-asserted-by":"crossref","unstructured":"Lu, Y., Wu, S., Tai, Y.W., Tang, C.K.: Image generation from sketch constraint using contextual gan. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 205\u2013220 (2018)","DOI":"10.1007\/978-3-030-01270-0_13"},{"issue":"1","key":"16_CR23","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1145\/3503250","volume":"65","author":"B Mildenhall","year":"2021","unstructured":"Mildenhall, B., Srinivasan, P.P., Tancik, M., Barron, J.T., Ramamoorthi, R., Ng, R.: Nerf: representing scenes as neural radiance fields for view synthesis. Commun. ACM 65(1), 99\u2013106 (2021)","journal-title":"Commun. ACM"},{"key":"16_CR24","doi-asserted-by":"crossref","unstructured":"Mou, C., Wang, X., Xie, L., Wu, Y., Zhang, J., Qi, Z., Shan, Y.: T2i-adapter: Learning adapters to dig out more controllable ability for text-to-image diffusion models. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a038, pp. 4296\u20134304 (2024)","DOI":"10.1609\/aaai.v38i5.28226"},{"key":"16_CR25","unstructured":"Podell, D., English, Z., Lacey, K., Blattmann, A., Dockhorn, T., M\u00fcller, J., Penna, J., Rombach, R.: Sdxl: Improving latent diffusion models for high-resolution image synthesis. arXiv preprint arXiv:2307.01952 (2023)"},{"key":"16_CR26","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"issue":"8","key":"16_CR27","first-page":"9","volume":"1","author":"A Radford","year":"2019","unstructured":"Radford, A., Wu, J., Child, R., Luan, D., Amodei, D., Sutskever, I., et al.: Language models are unsupervised multitask learners. OpenAI blog 1(8), 9 (2019)","journal-title":"OpenAI blog"},{"key":"16_CR28","doi-asserted-by":"crossref","unstructured":"Rezatofighi, H., Tsoi, N., Gwak, J., Sadeghian, A., Reid, I., Savarese, S.: Generalized intersection over union: a metric and a loss for bounding box regression. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 658\u2013666 (2019)","DOI":"10.1109\/CVPR.2019.00075"},{"key":"16_CR29","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_CR30","doi-asserted-by":"publisher","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","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"16_CR31","doi-asserted-by":"crossref","unstructured":"Sain, A., Bhunia, A.K., Chowdhury, P.N., Koley, S., Xiang, T., Song, Y.Z.: Clip for all things zero-shot sketch-based image retrieval, fine-grained or not. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2765\u20132775 (2023)","DOI":"10.1109\/CVPR52729.2023.00271"},{"key":"16_CR32","unstructured":"Vaswani, A.: Attention is all you need. Advances in Neural Information Processing Systems (2017)"},{"key":"16_CR33","doi-asserted-by":"crossref","unstructured":"Voynov, A., Aberman, K., Cohen-Or, D.: Sketch-guided text-to-image diffusion models. In: ACM SIGGRAPH 2023 Conference Proceedings, pp. 1\u201311 (2023)","DOI":"10.1145\/3588432.3591560"},{"key":"16_CR34","unstructured":"Wang, T., Zhang, T., Zhang, B., Ouyang, H., Chen, D., Chen, Q., Wen, F.: Pretraining is all you need for image-to-image translation. arXiv preprint arXiv:2205.12952 (2022)"},{"key":"16_CR35","unstructured":"Ye, H., Zhang, J., Liu, S., Han, X., Yang, W.: Ip-adapter: Text compatible image prompt adapter for text-to-image diffusion models. arXiv preprint arXiv:2308.06721 (2023)"},{"key":"16_CR36","doi-asserted-by":"crossref","unstructured":"Zhang, L., Rao, A., Agrawala, M.: Adding conditional control to text-to-image diffusion models. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3836\u20133847 (2023)","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"16_CR37","doi-asserted-by":"crossref","unstructured":"Zhang, T., Xie, X., Du, X., Xie, H.: Sketch-guided scene image generation. arXiv preprint arXiv:2407.06469 (2024)","DOI":"10.1016\/j.cag.2025.104226"},{"key":"16_CR38","unstructured":"Zhao, S., Chen, D., Chen, Y.C., Bao, J., Hao, S., Yuan, L., Wong, K.Y.K.: Uni-controlnet: all-in-one control to text-to-image diffusion models. Advances in Neural Information Processing Systems 36 (2024)"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition and Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-5693-9_16","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,20]],"date-time":"2026-01-20T21:22:34Z","timestamp":1768944154000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-5693-9_16"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9789819556922","9789819556939"],"references-count":38,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-5693-9_16","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"21 January 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chinese Conference on Pattern Recognition and Computer Vision  (PRCV)","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Shanghai","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":"15 October 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 October 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccprcv2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/2025.prcv.cn\/index.asp","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}