{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T13:26:01Z","timestamp":1780406761012,"version":"3.54.1"},"publisher-location":"New York, NY, USA","reference-count":53,"publisher":"ACM","funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62425209"],"award-info":[{"award-number":["62425209"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3755437","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T06:47:18Z","timestamp":1761374838000},"page":"10142-10151","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["CoProSketch: Controllable and Progressive Sketch Generation with Diffusion Model"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-3764-5170","authenticated-orcid":false,"given":"Ruohao","family":"Zhan","sequence":"first","affiliation":[{"name":"State Key Lab of CAD&CG, Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3366-093X","authenticated-orcid":false,"given":"Yijin","family":"Li","sequence":"additional","affiliation":[{"name":"Avolution AI, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4029-5494","authenticated-orcid":false,"given":"Yisheng","family":"He","sequence":"additional","affiliation":[{"name":"Alibaba Group, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6637-0109","authenticated-orcid":false,"given":"Shuo","family":"Chen","sequence":"additional","affiliation":[{"name":"State Key Lab of CAD&CG, Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-8879-4563","authenticated-orcid":false,"given":"Yichen","family":"Shen","sequence":"additional","affiliation":[{"name":"State Key Lab of CAD&CG, Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-9465-5726","authenticated-orcid":false,"given":"Xinyu","family":"Chen","sequence":"additional","affiliation":[{"name":"State Key Lab of CAD&CG, Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6833-9102","authenticated-orcid":false,"given":"Zilong","family":"Dong","sequence":"additional","affiliation":[{"name":"Alibaba Group, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7688-1471","authenticated-orcid":false,"given":"Zhaoyang","family":"Huang","sequence":"additional","affiliation":[{"name":"Avolution AI, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5661-8430","authenticated-orcid":false,"given":"Guofeng","family":"Zhang","sequence":"additional","affiliation":[{"name":"State Key Lab of CAD&CG, Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_2_1_1","volume-title":"An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv","author":"Alexey Dosovitskiy","year":"2010","unstructured":"Dosovitskiy Alexey. 2020. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv: 2010.11929 (2020)."},{"key":"e_1_3_2_2_2_1","unstructured":"cagliostrolab. 2024. cagliostrolab\/animagine-xl-3.1 \u00b7 Hugging Face. https:\/\/huggingface.co\/cagliostrolab\/animagine-xl-3.1"},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.1986.4767851"},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02062"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"crossref","unstructured":"Caroline Chan Fr\u00e9do Durand and Phillip Isola. 2022. Learning To Generate Line Drawings That Convey Geometry and Semantics. 7915-7925.","DOI":"10.1109\/CVPR52688.2022.00776"},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","unstructured":"Bo Cheng Yuhang Ma Liebucha Wu Shanyuan Liu Ao Ma Xiaoyu Wu Dawei Leng and Yuhui Yin. 2024. HiCo: Hierarchical Controllable Diffusion Model for Layout-to-image Generation. https:\/\/doi.org\/10.48550\/arXiv.2410.14324 arXiv:2410.14324 [cs].","DOI":"10.48550\/arXiv.2410.14324"},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","unstructured":"Jiaxin Cheng Xiao Liang Xingjian Shi Tong He Tianjun Xiao and Mu Li. 2023. LayoutDiffuse: Adapting Foundational Diffusion Models for Layout-to-Image Generation. https:\/\/doi.org\/10.48550\/arXiv.2302.08908 arXiv:2302.08908 [cs].","DOI":"10.48550\/arXiv.2302.08908"},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2345401"},{"key":"e_1_3_2_2_9_1","unstructured":"Kevin Frans L. B. Soros and Olaf Witkowski. 2021. CLIPDraw: Exploring Text-to-Drawing Synthesis through Language-Image Encoders. arXiv:2106.14843 [cs.CV] https:\/\/arxiv.org\/abs\/2106.14843"},{"key":"e_1_3_2_2_10_1","volume-title":"Prompt-to-prompt image editing with cross attention control. arXiv preprint arXiv:2208.01626","author":"Hertz Amir","year":"2022","unstructured":"Amir Hertz, Ron Mokady, Jay Tenenbaum, Kfir Aberman, Yael Pritch, and Daniel Cohen-Or. 2022. Prompt-to-prompt image editing with cross attention control. arXiv preprint arXiv:2208.01626 (2022)."},{"key":"e_1_3_2_2_11_1","first-page":"6840","volume-title":"Lin (Eds.)","volume":"33","author":"Ho Jonathan","year":"2020","unstructured":"Jonathan Ho, Ajay Jain, and Pieter Abbeel. 2020. Denoising Diffusion Probabilistic Models. In Advances in Neural Information Processing Systems, H. Larochelle, M. Ranzato, R. Hadsell, M.F. Balcan, and H. Lin (Eds.), Vol. 33. Curran Associates, Inc., 6840-6851. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2020\/file\/4c5bcfec8584af0d967f1ab10179ca4b-Paper.pdf"},{"key":"e_1_3_2_2_12_1","unstructured":"Ajay Jain Amber Xie and Pieter Abbeel. 2022. VectorFusion: Text-to-SVG by Abstracting Pixel-Based Diffusion Models. arXiv:2211.11319 [cs.CV] https:\/\/arxiv.org\/abs\/2211.11319"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00907"},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.3390\/math12020238"},{"key":"e_1_3_2_2_15_1","unstructured":"Taebum Kim. 2018. Anime Sketch Colorization Pair. https:\/\/www.kaggle.com\/datasets\/ktaebum\/anime-sketch-colorization-pair"},{"key":"e_1_3_2_2_16_1","volume-title":"Segment Anything. In Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV). 4015-4026","author":"Kirillov Alexander","year":"2023","unstructured":"Alexander Kirillov, Eric Mintun, Nikhila Ravi, Hanzi Mao, Chloe Rolland, Laura Gustafson, Tete Xiao, Spencer Whitehead, Alexander C. Berg, Wan-Yen Lo, Piotr Dollar, and Ross Girshick. 2023. Segment Anything. In Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV). 4015-4026."},{"key":"e_1_3_2_2_17_1","unstructured":"Kohya. 2024. kohya-ss\/sd-scripts. https:\/\/github.com\/kohya-ss\/sd-scripts"},{"key":"e_1_3_2_2_18_1","volume-title":"Visual Saliency Based on Multiscale Deep Features. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 5455-5463","author":"Li G.","unstructured":"G. Li and Y. Yu. 2015. Visual Saliency Based on Multiscale Deep Features. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 5455-5463."},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2019.00154"},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00162"},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00007"},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00951"},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"crossref","unstructured":"William E Lorensen and Harvey E Cline. 1998. Marching cubes: A high resolution 3D surface construction algorithm. In Seminal graphics: pioneering efforts that shaped the field. 347-353.","DOI":"10.1145\/280811.281026"},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2019.8803506"},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3478512.3488607"},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00025"},{"key":"e_1_3_2_2_28_1","volume-title":"SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis. arXiv:2307.01952 [cs.CV] https:\/\/arxiv.org\/abs\/2307.01952","author":"Podell Dustin","year":"2023","unstructured":"Dustin Podell, Zion English, Kyle Lacey, Andreas Blattmann, Tim Dockhorn, Jonas M\u00fcller, Joe Penna, and Robin Rombach. 2023. SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis. arXiv:2307.01952 [cs.CV] https:\/\/arxiv.org\/abs\/2307.01952"},{"key":"e_1_3_2_2_29_1","volume-title":"Proceedings of the 38th International Conference on Machine Learning (Proceedings of Machine Learning Research","volume":"8763","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, Gretchen Krueger, and Ilya Sutskever. 2021. Learning Transferable Visual Models From Natural Language Supervision. In Proceedings of the 38th International Conference on Machine Learning (Proceedings of Machine Learning Research, Vol. 139), Marina Meila and Tong Zhang (Eds.). PMLR, 8748-8763. https:\/\/proceedings.mlr.press\/v139\/radford21a.html"},{"key":"e_1_3_2_2_30_1","unstructured":"Nikhila Ravi Valentin Gabeur Yuan-Ting Hu Ronghang Hu Chaitanya Ryali Tengyu Ma Haitham Khedr Roman R\u00e4dle Chloe Rolland Laura Gustafson et al. 2024. Sam 2: Segment anything in images and videos. arXiv preprint arXiv:2408.00714 (2024)."},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_2_2_32_1","unstructured":"Christoph Schuhmann. 2022. christophschuhmann\/improved-aesthetic-predictor: CLIPMLP Aesthetic Score Predictor. https:\/\/github.com\/christophschuhmann\/improved-aesthetic-predictor"},{"key":"e_1_3_2_2_33_1","volume-title":"Hierarchical image saliency detection on extended CSSD","author":"Shi Jianping","year":"2015","unstructured":"Jianping Shi, Qiong Yan, Li Xu, and Jiaya Jia. 2015. Hierarchical image saliency detection on extended CSSD. IEEE transactions on pattern analysis and machine intelligence, Vol. 38, 4 (2015), 717-729."},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00844"},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cag.2023.05.010"},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00383"},{"key":"e_1_3_2_2_37_1","volume-title":"Amit Haim Bermano, Daniel Cohen-Or, Amir Zamir, and Ariel Shamir.","author":"Vinker Yael","year":"2022","unstructured":"Yael Vinker, Ehsan Pajouheshgar, Jessica Y. Bo, Roman Christian Bachmann, Amit Haim Bermano, Daniel Cohen-Or, Amir Zamir, and Ariel Shamir. 2022. CLIPasso: Semantically-Aware Object Sketching. http:\/\/arxiv.org\/abs\/2202.05822 arXiv:2202.05822."},{"key":"e_1_3_2_2_38_1","volume-title":"Kristine Zheng, Alex Zhao, Judith E Fan, and Antonio Torralba.","author":"Vinker Yael","year":"2024","unstructured":"Yael Vinker, Tamar Rott Shaham, Kristine Zheng, Alex Zhao, Judith E Fan, and Antonio Torralba. 2024. SketchAgent: Language-Driven Sequential Sketch Generation. arXiv:2411.17673 [cs.CV] https:\/\/arxiv.org\/abs\/2411.17673"},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"crossref","unstructured":"Lijun Wang Huchuan Lu Yifan Wang Mengyang Feng Dong Wang Baocai Yin and Xiang Ruan. 2017. Learning to Detect Salient Objects with Image-level Supervision. In CVPR.","DOI":"10.1109\/CVPR.2017.404"},{"key":"e_1_3_2_2_40_1","volume-title":"Neus: Learning neural implicit surfaces by","author":"Wang Peng","year":"2021","unstructured":"Peng Wang, Lingjie Liu, Yuan Liu, Christian Theobalt, Taku Komura, and Wenping Wang. 2021. Neus: Learning neural implicit surfaces by volume rendering for multi-view reconstruction. arXiv preprint arXiv:2106.10689 (2021)."},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.3389\/frsip.2024.1356793"},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cag.2012.03.004"},{"key":"e_1_3_2_2_43_1","unstructured":"Ximing Xing Chuang Wang Haitao Zhou Jing Zhang Qian Yu and Dong Xu. 2024. DiffSketcher: Text Guided Vector Sketch Synthesis through Latent Diffusion Models. http:\/\/arxiv.org\/abs\/2306.14685 arXiv:2306.14685 [cs]."},{"key":"e_1_3_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20206"},{"key":"e_1_3_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.153"},{"key":"e_1_3_2_2_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.407"},{"key":"e_1_3_2_2_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/3554729"},{"key":"e_1_3_2_2_48_1","unstructured":"Zhuoyi Yang Jiayan Teng Wendi Zheng Ming Ding Shiyu Huang Jiazheng Xu Yuanming Yang Wenyi Hong Xiaohan Zhang Guanyu Feng Da Yin Xiaotao Gu Yuxuan Zhang Weihan Wang Yean Cheng Ting Liu Bin Xu Yuxiao Dong and Jie Tang. 2024. CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer. arXiv:2408.06072 [cs.CV] https:\/\/arxiv.org\/abs\/2408.06072"},{"key":"e_1_3_2_2_49_1","volume-title":"Ip-adapter: Text compatible image prompt adapter for text-to-image diffusion models. arXiv preprint arXiv:2308.06721","author":"Ye Hu","year":"2023","unstructured":"Hu Ye, Jun Zhang, Sibo Liu, Xiao Han, and Wei Yang. 2023. Ip-adapter: Text compatible image prompt adapter for text-to-image diffusion models. arXiv preprint arXiv:2308.06721 (2023)."},{"key":"e_1_3_2_2_50_1","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR).","author":"Yi Ran","unstructured":"Ran Yi, Yong-Jin Liu, Yu-Kun Lai, and Paul L. Rosin. 2019. APDrawingGAN: Generating Artistic Portrait Drawings From Face Photos With Hierarchical GANs. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)."},{"key":"e_1_3_2_2_51_1","volume-title":"Sung-Ho Bae, Seungkyu Lee, and Choong Seon Hong.","author":"Zhang Chaoning","year":"2023","unstructured":"Chaoning Zhang, Dongshen Han, Yu Qiao, Jung Uk Kim, Sung-Ho Bae, Seungkyu Lee, and Choong Seon Hong. 2023a. Faster Segment Anything: Towards Lightweight SAM for Mobile Applications. arXiv:2306.14289 [cs.CV] https:\/\/arxiv.org\/abs\/2306.14289"},{"key":"e_1_3_2_2_52_1","doi-asserted-by":"crossref","unstructured":"Lvmin Zhang Anyi Rao and Maneesh Agrawala. 2023b. Adding Conditional Control to Text-to-Image Diffusion Models. http:\/\/arxiv.org\/abs\/2302.05543 arXiv:2302.05543.","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"e_1_3_2_2_53_1","doi-asserted-by":"publisher","unstructured":"Guangcong Zheng Xianpan Zhou Xuewei Li Zhongang Qi Ying Shan and Xi Li. 2024. LayoutDiffusion: Controllable Diffusion Model for Layout-to-image Generation. https:\/\/doi.org\/10.48550\/arXiv.2303.17189 arXiv:2303.17189 [cs].","DOI":"10.48550\/arXiv.2303.17189"}],"event":{"name":"MM '25: The 33rd ACM International Conference on Multimedia","location":"Dublin Ireland","acronym":"MM '25","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3755437","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T04:14:15Z","timestamp":1765340055000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3755437"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":53,"alternative-id":["10.1145\/3746027.3755437","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3755437","relation":{},"subject":[],"published":{"date-parts":[[2025,10,27]]},"assertion":[{"value":"2025-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}