{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,22]],"date-time":"2026-07-22T16:40:25Z","timestamp":1784738425275,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":36,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,11]],"date-time":"2024-10-11T00:00:00Z","timestamp":1728604800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,13]]},"DOI":"10.1145\/3654777.3676444","type":"proceedings-article","created":{"date-parts":[[2024,10,11]],"date-time":"2024-10-11T10:50:36Z","timestamp":1728643836000},"page":"1-13","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":23,"title":["Block and Detail: Scaffolding Sketch-to-Image Generation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-9809-9994","authenticated-orcid":false,"given":"Vishnu","family":"Sarukkai","sequence":"first","affiliation":[{"name":"Computer Science, Stanford University, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-6399-4337","authenticated-orcid":false,"given":"Lu","family":"Yuan","sequence":"additional","affiliation":[{"name":"Stanford University, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-3553-3732","authenticated-orcid":false,"given":"Mia","family":"Tang","sequence":"additional","affiliation":[{"name":"Stanford University, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8996-7327","authenticated-orcid":false,"given":"Maneesh","family":"Agrawala","sequence":"additional","affiliation":[{"name":"Stanford University, United States and Roblox, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8754-0429","authenticated-orcid":false,"given":"Kayvon","family":"Fatahalian","sequence":"additional","affiliation":[{"name":"Stanford University, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,10,11]]},"reference":[{"key":"e_1_3_2_2_1_1","unstructured":"2023. ControlNet Mysee - Light and Dark - Squint Illusions Hidden Symbols Subliminal Text QR Codes. Accessed: 2024-01-23."},{"key":"e_1_3_2_2_2_1","unstructured":"2023. Controlnet QR Pattern (QR Codes). Accessed: 2024-01-23."},{"key":"e_1_3_2_2_3_1","unstructured":"2023. Dreamshaper 7. Accessed: 2024-04-01."},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3592450"},{"key":"e_1_3_2_2_5_1","unstructured":"Yogesh Balaji Seungjun Nah Xun Huang Arash Vahdat Jiaming Song Qinsheng Zhang Karsten Kreis Miika Aittala Timo Aila Samuli Laine Bryan Catanzaro Tero Karras and Ming-Yu Liu. 2023. eDiff-I: Text-to-Image Diffusion Models with an Ensemble of Expert Denoisers. arxiv:2211.01324\u00a0[cs.CV]"},{"key":"e_1_3_2_2_6_1","volume-title":"Proceedings of the 40th International Conference on Machine Learning","author":"Bar-Tal Omer","year":"2023","unstructured":"Omer Bar-Tal, Lior Yariv, Yaron Lipman, and Tali Dekel. 2023. MultiDiffusion: fusing diffusion paths for controlled image generation. In Proceedings of the 40th International Conference on Machine Learning (Honolulu, Hawaii, USA) (ICML\u201923). JMLR.org, Article 74, 16\u00a0pages."},{"key":"e_1_3_2_2_7_1","unstructured":"Erik Barrett. 2021. How To Draw Everything: Simple Sketching And Inking Step By Step Lessons."},{"key":"e_1_3_2_2_8_1","unstructured":"Shariq\u00a0Farooq Bhat Niloy\u00a0J. Mitra and Peter Wonka. 2023. LooseControl: Lifting ControlNet for Generalized Depth Conditioning. arxiv:2312.03079\u00a0[cs.CV]"},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612524"},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00981"},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00404"},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2892301"},{"key":"e_1_3_2_2_13_1","volume-title":"Keys to drawing","author":"Dodson Bert","unstructured":"Bert Dodson. 1990. Keys to drawing. Penguin."},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR56361.2022.9956233"},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/2047196.2047245"},{"key":"e_1_3_2_2_16_1","unstructured":"Aaron Hertzmann. 2022. Toward Modeling Creative Processes for Algorithmic Painting. arxiv:2205.01605\u00a0[cs.AI]"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/2501988.2501997"},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.632"},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/2010324.1964922"},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/2461912.2462016"},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16304"},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/2630099.2630103"},{"key":"e_1_3_2_2_23_1","volume-title":"Proceedings, Part III 16","author":"Liu Runtao","year":"2020","unstructured":"Runtao Liu, Qian Yu, and Stella\u00a0X Yu. 2020. Unsupervised sketch to photo synthesis. In Computer Vision\u2013ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part III 16. Springer, 36\u201352."},{"key":"e_1_3_2_2_24_1","volume-title":"DrawFromDrawings: 2D drawing assistance via stroke interpolation with a sketch database","author":"Matsui Yusuke","year":"2016","unstructured":"Yusuke Matsui, Takaaki Shiratori, and Kiyoharu Aizawa. 2016. DrawFromDrawings: 2D drawing assistance via stroke interpolation with a sketch database. IEEE transactions on visualization and computer graphics 23, 7 (2016), 1852\u20131862."},{"key":"e_1_3_2_2_25_1","volume-title":"Sdedit: Guided image synthesis and editing with stochastic differential equations. arXiv preprint arXiv:2108.01073","author":"Meng Chenlin","year":"2021","unstructured":"Chenlin Meng, Yutong He, Yang Song, Jiaming Song, Jiajun Wu, Jun-Yan Zhu, and Stefano Ermon. 2021. Sdedit: Guided image synthesis and editing with stochastic differential equations. arXiv preprint arXiv:2108.01073 (2021)."},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3450626.3459833"},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1037\/0096-3445.116.1.50"},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3306305.3332370"},{"key":"e_1_3_2_2_29_1","volume-title":"U2-Net: Going deeper with nested U-structure for salient object detection. Pattern recognition 106","author":"Qin Xuebin","year":"2020","unstructured":"Xuebin Qin, Zichen Zhang, Chenyang Huang, Masood Dehghan, Osmar\u00a0R Zaiane, and Martin Jagersand. 2020. U2-Net: Going deeper with nested U-structure for salient object detection. Pattern recognition 106 (2020), 107404."},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00416"},{"key":"e_1_3_2_2_32_1","unstructured":"Christoph Schuhmann Romain Beaumont Richard Vencu Cade Gordon Ross Wightman Mehdi Cherti Theo Coombes Aarush Katta Clayton Mullis Mitchell Wortsman 2022. LAION-5B: An open large-scale dataset for training next generation image-text models. https:\/\/ar5iv.org\/abs\/2210.08402."},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","unstructured":"Barbara Tversky and Masaki Suwa. 2009. Thinking with Sketches. https:\/\/doi.org\/10.1093\/acprof:oso\/9780195381634.003.0004","DOI":"10.1093\/acprof:oso\/9780195381634.003.0004"},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3588432.3591560"},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.244"}],"event":{"name":"UIST '24: The 37th Annual ACM Symposium on User Interface Software and Technology","location":"Pittsburgh PA USA","acronym":"UIST '24"},"container-title":["Proceedings of the 37th Annual ACM Symposium on User Interface Software and Technology"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3654777.3676444","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3654777.3676444","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,4]],"date-time":"2025-08-04T21:14:06Z","timestamp":1754342046000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3654777.3676444"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,11]]},"references-count":36,"alternative-id":["10.1145\/3654777.3676444","10.1145\/3654777"],"URL":"https:\/\/doi.org\/10.1145\/3654777.3676444","relation":{},"subject":[],"published":{"date-parts":[[2024,10,11]]},"assertion":[{"value":"2024-10-11","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}