{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,24]],"date-time":"2025-08-24T00:02:27Z","timestamp":1755993747798,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":34,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"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]]},"DOI":"10.1145\/3703619.3706048","type":"proceedings-article","created":{"date-parts":[[2025,1,19]],"date-time":"2025-01-19T18:20:52Z","timestamp":1737310852000},"page":"1-7","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Multiscale Structure Prompted Diffusion Models for Scene Text Image Super-Resolution"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-7899-1615","authenticated-orcid":false,"given":"Huilong","family":"Xie","sequence":"first","affiliation":[{"name":"Dalian University, Dalian, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6299-2795","authenticated-orcid":false,"given":"Wanshu","family":"Fan Fan","sequence":"additional","affiliation":[{"name":"School of Software Engineering, Dalian University, Dalian, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3414-9623","authenticated-orcid":false,"given":"Dongsheng","family":"Zhou","sequence":"additional","affiliation":[{"name":"Dalian University, Dalian, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,1,19]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"crossref","unstructured":"Jingye Chen Bin Li and Xiangyang Xue. 2021. Scene Text Telescope: Text-Focused Scene Image Super-Resolution. In CVPR. 12026\u201312035.","DOI":"10.1109\/CVPR46437.2021.01185"},{"key":"e_1_3_2_1_2_1","volume-title":"AON: Towards Arbitrarily-Oriented Text Recognition. In CVPR. 5571\u20135579.","author":"Cheng Zhanzhan","year":"2018","unstructured":"Zhanzhan Cheng, Yangliu Xu, Fan Bai, Yi Niu, Shiliang Pu, and Shuigeng Zhou. 2018. AON: Towards Arbitrarily-Oriented Text Recognition. In CVPR. 5571\u20135579."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"crossref","unstructured":"Tao Dai Jianrui Cai Yongbing Zhang Shu-Tao Xia and Lei Zhang. 2019. Second-Order Attention Network for Single Image Super-Resolution. In CVPR. 11065\u201311074.","DOI":"10.1109\/CVPR.2019.01132"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2439281"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"crossref","unstructured":"Berthy\u00a0T. Feng Jamie Smith Michael Rubinstein Huiwen Chang Katherine\u00a0L. Bouman and William\u00a0T. Freeman. 2023. Score-Based Diffusion Models as Principled Priors for Inverse Imaging. In ICCV. 10486\u201310497.","DOI":"10.1109\/ICCV51070.2023.00965"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"crossref","unstructured":"Hang Guo Tao Dai Guanghao Meng and Shu-Tao Xia. 2023. Towards Robust Scene Text Image Super-resolution via Explicit Location Enhancement. In IJCAI. 782\u2013790.","DOI":"10.24963\/ijcai.2023\/87"},{"key":"e_1_3_2_1_7_1","unstructured":"Jonathan Ho Ajay Jain and Pieter Abbeel. 2020. Denoising Diffusion Probabilistic Models. In NeurIPS."},{"key":"e_1_3_2_1_8_1","volume-title":"Cascaded Diffusion Models for High Fidelity Image Generation. JMLR 23","author":"Ho Jonathan","year":"2022","unstructured":"Jonathan Ho, Chitwan Saharia, William Chan, David\u00a0J. Fleet, Mohammad Norouzi, and Tim Salimans. 2022. Cascaded Diffusion Models for High Fidelity Image Generation. JMLR 23 (2022), 47:1\u201347:33."},{"key":"e_1_3_2_1_9_1","volume-title":"Ccnet: Criss-cross attention for semantic segmentation. In ICCV. 603\u2013612.","author":"Huang Zilong","year":"2019","unstructured":"Zilong Huang, Xinggang Wang, Lichao Huang, Chang Huang, Yunchao Wei, and Wenyu Liu. 2019. Ccnet: Criss-cross attention for semantic segmentation. In ICCV. 603\u2013612."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1049\/el:20080522"},{"key":"e_1_3_2_1_11_1","volume-title":"Kingma and Jimmy Ba","author":"P.","year":"2015","unstructured":"Diederik\u00a0P. Kingma and Jimmy Ba. 2015. Adam: A Method for Stochastic Optimization. In ICLR."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"crossref","unstructured":"Wei-Sheng Lai Jia-Bin Huang Narendra Ahuja and Ming-Hsuan Yang. 2017. Deep Laplacian Pyramid Networks for Fast and Accurate Super-Resolution. In CVPR. 5835\u20135843.","DOI":"10.1109\/CVPR.2017.618"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"crossref","unstructured":"Christian Ledig Lucas Theis Ferenc Huszar Jose Caballero Andrew Cunningham Alejandro Acosta Andrew\u00a0P. Aitken Alykhan Tejani Johannes Totz Zehan Wang and Wenzhe Shi. 2017. Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network. In CVPR. 105\u2013114.","DOI":"10.1109\/CVPR.2017.19"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.01.029"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2019.01.020"},{"key":"e_1_3_2_1_16_1","first-page":"1341","article-title":"Text Prior Guided Scene Text Image Super-Resolution","volume":"32","author":"Ma Jianqi","year":"2023","unstructured":"Jianqi Ma, Shi Guo, and Lei Zhang. 2023. Text Prior Guided Scene Text Image Super-Resolution. IEEE TIP 32 (2023), 1341\u20131353.","journal-title":"IEEE TIP"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"crossref","unstructured":"Jianqi Ma Zhetong Liang and Lei Zhang. 2022. A Text Attention Network for Spatial Deformation Robust Scene Text Image Super-resolution. In CVPR. 5901\u20135910.","DOI":"10.1109\/CVPR52688.2022.00582"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"crossref","unstructured":"Robin Rombach Andreas Blattmann Dominik Lorenz Patrick Esser and Bj\u00f6rn Ommer. 2022. High-Resolution Image Synthesis with Latent Diffusion Models. In CVPR. 10674\u201310685.","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_2_1_19_1","first-page":"1","article-title":"Palette","volume":"15","author":"Saharia Chitwan","year":"2022","unstructured":"Chitwan Saharia, William Chan, Huiwen Chang, Chris\u00a0A. Lee, Jonathan Ho, Tim Salimans, David\u00a0J. Fleet, and Mohammad Norouzi. 2022. Palette: Image-to-Image Diffusion Models. In SIGGRAPH. 15:1\u201315:10.","journal-title":"Image-to-Image Diffusion Models. In SIGGRAPH."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2646371"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2848939"},{"key":"e_1_3_2_1_22_1","unstructured":"Jascha Sohl-Dickstein Eric\u00a0A. Weiss Niru Maheswaranathan and Surya Ganguli. 2015. Deep Unsupervised Learning using Nonequilibrium Thermodynamics. In ICML Vol.\u00a037. 2256\u20132265."},{"key":"e_1_3_2_1_23_1","volume-title":"Exploiting Diffusion Prior for Real-World Image Super-Resolution. arXiv:2305.07015","author":"Wang Jianyi","year":"2023","unstructured":"Jianyi Wang, Zongsheng Yue, Shangchen Zhou, Kelvin C.\u00a0K. Chan, and Chen\u00a0Change Loy. 2023b. Exploiting Diffusion Prior for Real-World Image Super-Resolution. arXiv:2305.07015 (2023)."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"crossref","unstructured":"Wenjia Wang Enze Xie Xuebo Liu Wenhai Wang Ding Liang Chunhua Shen and Xiang Bai. 2020. Scene Text Image Super-Resolution in the Wild. In ECCV Vol.\u00a012355. 650\u2013666.","DOI":"10.1007\/978-3-030-58607-2_38"},{"key":"e_1_3_2_1_25_1","volume-title":"SinSR: Diffusion-Based Image Super-Resolution in a Single Step. arXiv:2311.14760","author":"Wang Yufei","year":"2023","unstructured":"Yufei Wang, Wenhan Yang, Xinyuan Chen, Yaohui Wang, Lanqing Guo, Lap-Pui Chau, Ziwei Liu, Yu Qiao, Alex\u00a0C. Kot, and Bihan Wen. 2023a. SinSR: Diffusion-Based Image Super-Resolution in a Single Step. arXiv:2311.14760 (2023)."},{"key":"e_1_3_2_1_26_1","first-page":"600","article-title":"Image quality assessment: from error visibility to structural similarity","volume":"13","author":"Wang Zhou","year":"2004","unstructured":"Zhou Wang, Alan\u00a0C. Bovik, Hamid\u00a0R. Sheikh, and Eero\u00a0P. Simoncelli. 2004. Image quality assessment: from error visibility to structural similarity. IEEE TIP 13, 4 (2004), 600\u2013612.","journal-title":"IEEE TIP"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"crossref","unstructured":"Bin Xia Yulun Zhang Shiyin Wang Yitong Wang Xinglong Wu Yapeng Tian Wenming Yang and Luc\u00a0Van Gool. 2023. DiffIR: Efficient Diffusion Model for Image Restoration. In ICCV. 13049\u201313059.","DOI":"10.1109\/ICCV51070.2023.01204"},{"key":"e_1_3_2_1_28_1","volume-title":"Resreshh: Efficient Diffusion Model for Image Super-resolution by Residual Shifting. In NeurIPS.","author":"Yue Zongsheng","year":"2023","unstructured":"Zongsheng Yue, Jianyi Wang, and Chen\u00a0Change Loy. 2023. Resreshh: Efficient Diffusion Model for Image Super-resolution by Residual Shifting. In NeurIPS."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"crossref","unstructured":"Yulun Zhang Kunpeng Li Kai Li Lichen Wang Bineng Zhong and Yun Fu. 2018a. Image Super-Resolution Using Very Deep Residual Channel Attention Networks. In ECCV Vol.\u00a011211. 294\u2013310.","DOI":"10.1007\/978-3-030-01234-2_18"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"crossref","unstructured":"Yulun Zhang Yapeng Tian Yu Kong Bineng Zhong and Yun Fu. 2018b. Residual Dense Network for Image Super-Resolution. In CVPR. 2472\u20132481.","DOI":"10.1109\/CVPR.2018.00262"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"crossref","unstructured":"Cairong Zhao Shuyang Feng Brian\u00a0Nlong Zhao Zhijun Ding Jun Wu Fumin Shen and Heng\u00a0Tao Shen. 2021. Scene Text Image Super-Resolution via Parallelly Contextual Attention Network. In ACM MM. 2908\u20132917.","DOI":"10.1145\/3474085.3475469"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"crossref","unstructured":"Minyi Zhao Miao Wang Fan Bai Bingjia Li Jie Wang and Shuigeng Zhou. 2022. C3-STISR: Scene Text Image Super-resolution with Triple Clues. In IJCAI. 1707\u20131713.","DOI":"10.24963\/ijcai.2022\/238"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"crossref","unstructured":"Shipeng Zhu Zuoyan Zhao Pengfei Fang and Hui Xue. 2023b. Improving Scene Text Image Super-resolution via Dual Prior Modulation Network. In AAAI. 3843\u20133851.","DOI":"10.1609\/aaai.v37i3.25497"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"crossref","unstructured":"Xiangyuan Zhu Kehua Guo Hui Fang Rui Ding Zheng Wu and Gerald Schaefer. 2023a. Gradient-Based Graph Attention for Scene Text Image Super-resolution. In AAAI. 3861\u20133869.","DOI":"10.1609\/aaai.v37i3.25499"}],"event":{"name":"VRCAI '24: The 19th ACM SIGGRAPH International Conference on Virtual-Reality Continuum and its Applications in Industry","sponsor":["SIGGRAPH ACM Special Interest Group on Computer Graphics and Interactive Techniques"],"location":"Nanjing Guangdong Province China","acronym":"VRCAI '24"},"container-title":["Proceedings of the 19th ACM SIGGRAPH International Conference on Virtual-Reality Continuum and its Applications in Industry"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3703619.3706048","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3703619.3706048","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T02:08:22Z","timestamp":1755914902000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3703619.3706048"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12]]},"references-count":34,"alternative-id":["10.1145\/3703619.3706048","10.1145\/3703619"],"URL":"https:\/\/doi.org\/10.1145\/3703619.3706048","relation":{},"subject":[],"published":{"date-parts":[[2024,12]]},"assertion":[{"value":"2025-01-19","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}