{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,13]],"date-time":"2026-06-13T09:32:52Z","timestamp":1781343172096,"version":"3.54.1"},"publisher-location":"New York, NY, USA","reference-count":20,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,11,19]],"date-time":"2024-11-19T00:00:00Z","timestamp":1731974400000},"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":[[2024,12,3]]},"DOI":"10.1145\/3681758.3698008","type":"proceedings-article","created":{"date-parts":[[2024,11,19]],"date-time":"2024-11-19T19:12:11Z","timestamp":1732043531000},"page":"1-4","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["OrienText: Surface Oriented Textual Image Generation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1532-801X","authenticated-orcid":false,"given":"Shubham Singh","family":"Paliwal","sequence":"first","affiliation":[{"name":"TCS Research, New Delhi, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4853-512X","authenticated-orcid":false,"given":"Arushi","family":"Jain","sequence":"additional","affiliation":[{"name":"TCS Research, New Delhi, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-7326-4039","authenticated-orcid":false,"given":"Monika","family":"Sharma","sequence":"additional","affiliation":[{"name":"TCS Research, New Delhi, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7081-1701","authenticated-orcid":false,"given":"Vikram","family":"Jamwal","sequence":"additional","affiliation":[{"name":"TCS Research, New Delhi, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9834-3308","authenticated-orcid":false,"given":"Lovekesh","family":"Vig","sequence":"additional","affiliation":[{"name":"TCS Research, New Delhi, India"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,11,19]]},"reference":[{"key":"e_1_3_3_2_2_1","volume-title":"Adobe Photoshop","author":"Inc. Adobe","year":"2023","unstructured":"Adobe Inc.2023. Adobe Photoshop."},{"key":"e_1_3_3_2_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00911"},{"key":"e_1_3_3_2_4_1","unstructured":"James Betker and Gabriel et\u00a0al. Goh. 2023. Improving image generation with better captions. Computer Science 2 (2023) 3."},{"key":"e_1_3_3_2_5_1","unstructured":"Jingye Chen Yupan Huang Tengchao Lv Lei Cui and Qifeng Chen. 2024. Textdiffuser: Diffusion models as text painters. Advances in NeurIPS 36 (2024)."},{"key":"e_1_3_3_2_6_1","unstructured":"Jingye Chen Yupan Huang Tengchao Lv Lei Cui Qifeng Chen and Furu Wei. 2023. TextDiffuser: Diffusion Models as Text Painters. arXiv (2023)."},{"key":"e_1_3_3_2_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.304"},{"key":"e_1_3_3_2_8_1","unstructured":"Jonathan Ho Ajay Jain and Pieter Abbeel. 2020. Denoising diffusion probabilistic models. Advances in neural information processing systems 33 (2020) 6840\u20136851."},{"key":"e_1_3_3_2_9_1","doi-asserted-by":"crossref","unstructured":"Zeyu Liu Weicong Liang Zhanhao Liang Chong Luo Ji Li Gao Huang and Yuhui Yuan. 2024. Glyph-ByT5: A Customized Text Encoder for Accurate Visual Text Rendering. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2403.09622 (2024).","DOI":"10.1007\/978-3-031-73226-3_21"},{"key":"e_1_3_3_2_10_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_5"},{"key":"e_1_3_3_2_11_1","unstructured":"Jian Ma Mingjun Zhao Chen Chen and Ruichen Wang. 2023. GlyphDraw: Learning to Draw Chinese Characters in Image Synthesis Models Coherently. arXiv preprint (2023)."},{"key":"e_1_3_3_2_12_1","doi-asserted-by":"crossref","unstructured":"Shubham Paliwal Arushi Jain Monika Sharma Vikram Jamwal and Lovekesh Vig. 2024. CustomText: Customized Textual Image Generation using Diffusion Models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2405.12531 (2024).","DOI":"10.1145\/3681758.3698008"},{"key":"e_1_3_3_2_13_1","unstructured":"Aditya Ramesh Prafulla Dhariwal Alex Nichol Casey Chu and Mark Chen. 2022. Hierarchical text-conditional image generation with clip latents. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2204.06125 1 2 (2022) 3."},{"key":"e_1_3_3_2_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_3_2_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"e_1_3_3_2_16_1","unstructured":"Chitwan Saharia William Chan Saurabh Saxena Lala Li Jay Whang Emily\u00a0L Denton Kamyar Ghasemipour Raphael Gontijo\u00a0Lopes Burcu Karagol\u00a0Ayan Tim Salimans et\u00a0al. 2022. Photorealistic text-to-image diffusion models with deep language understanding. Advances in NeurIPS 35 (2022) 36479\u201336494."},{"key":"e_1_3_3_2_17_1","unstructured":"Yang Song Prafulla Dhariwal Mark Chen and Ilya Sutskever. 2023. Consistency models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2303.01469 (2023)."},{"key":"e_1_3_3_2_18_1","doi-asserted-by":"crossref","unstructured":"Shang Sun Dan Xu Hao Wu Haocong Ying and Yurui Mou. 2022. Multi-view stereo for large-scale scene reconstruction with MRF-based depth inference. Computers & Graphics 106 (2022) 248\u2013258.","DOI":"10.1016\/j.cag.2022.06.009"},{"key":"e_1_3_3_2_19_1","unstructured":"Yuxiang Tuo Wangmeng Xiang Jun-Yan He Yifeng Geng and Xuansong Xie. 2023. Anytext: Multilingual visual text generation and editing. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2311.03054 (2023)."},{"key":"e_1_3_3_2_20_1","doi-asserted-by":"crossref","unstructured":"Xuyong Yang Tao Mei Ying-Qing Xu Yong Rui and Shipeng Li. 2016. Automatic generation of visual-textual presentation layout. ACM Transactions on Multimedia Computing Communications and Applications (TOMM) 12 2 (2016) 1\u201322.","DOI":"10.1145\/2818709"},{"key":"e_1_3_3_2_21_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28550"}],"event":{"name":"SA '24: SIGGRAPH Asia 2024 Technical Communications","location":"Tokyo Japan","acronym":"SA '24","sponsor":["SIGGRAPH ACM Special Interest Group on Computer Graphics and Interactive Techniques"]},"container-title":["SIGGRAPH Asia 2024 Technical Communications"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3681758.3698008","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3681758.3698008","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:18:15Z","timestamp":1750295895000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3681758.3698008"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,19]]},"references-count":20,"alternative-id":["10.1145\/3681758.3698008","10.1145\/3681758"],"URL":"https:\/\/doi.org\/10.1145\/3681758.3698008","relation":{},"subject":[],"published":{"date-parts":[[2024,11,19]]},"assertion":[{"value":"2024-11-19","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}