{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T06:08:20Z","timestamp":1784268500999,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":41,"publisher":"ACM","funder":[{"DOI":"10.13039\/501100003819","name":"Natural Science Foundation of Hubei Province","doi-asserted-by":"publisher","award":["2023BAB160"],"award-info":[{"award-number":["2023BAB160"]}],"id":[{"id":"10.13039\/501100003819","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62272349"],"award-info":[{"award-number":["62272349"]}],"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\/3746027.3755278","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T07:26:38Z","timestamp":1761377198000},"page":"9969-9977","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Bridging the Gap: Consistent Image Outpainting via Training-Free Noise Optimization"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-3394-0056","authenticated-orcid":false,"given":"Na","family":"Li","sequence":"first","affiliation":[{"name":"Key Laboratory of Aerospace Information Security and Trusted Computing, Ministry of Education, School of Cyber Science and Engineering, Wuhan University, Wuhan, Hubei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1802-4284","authenticated-orcid":false,"given":"Zihao","family":"Li","sequence":"additional","affiliation":[{"name":"Key Laboratory of Aerospace Information Security and Trusted Computing, Ministry of Education, School of Cyber Science and Engineering, Wuhan University, Wuhan, Hubei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-8335-1157","authenticated-orcid":false,"given":"Zuoli","family":"Tang","sequence":"additional","affiliation":[{"name":"Key Laboratory of Aerospace Information Security and Trusted Computing, Ministry of Education, School of Cyber Science and Engineering, Wuhan University, Wuhan, Hubei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-7036-6075","authenticated-orcid":false,"given":"Yuqing","family":"Yu","sequence":"additional","affiliation":[{"name":"Key Laboratory of Aerospace Information Security and Trusted Computing, Ministry of Education, School of Cyber Science and Engineering, Wuhan University, Wuhan, Hubei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6755-871X","authenticated-orcid":false,"given":"Lixin","family":"Zou","sequence":"additional","affiliation":[{"name":"Key Laboratory of Aerospace Information Security and Trusted Computing, Ministry of Education, School of Cyber Science and Engineering, Wuhan University, Wuhan, Hubei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3144-6374","authenticated-orcid":false,"given":"Chenliang","family":"Li","sequence":"additional","affiliation":[{"name":"Key Laboratory of Aerospace Information Security and Trusted Computing, Ministry of Education, School of Cyber Science and Engineering, Wuhan University, Wuhan, Hubei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Donghoon Ahn Jiwon Kang Sanghyun Lee Jaewon Min Minjae Kim Wooseok Jang Hyoungwon Cho Sayak Paul SeonHwa Kim Eunju Cha et al. 2024. A noise is worth diffusion guidance. arXiv preprint arXiv:2412.03895 (2024)."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02062"},{"key":"e_1_3_2_1_3_1","volume-title":"Attend-and-excite: Attention-based semantic guidance for text-to-image diffusion models. ACM transactions on Graphics (TOG)","author":"Chefer Hila","year":"2023","unstructured":"Hila Chefer, Yuval Alaluf, Yael Vinker, Lior Wolf, and Daniel Cohen-Or. 2023. Attend-and-excite: Attention-based semantic guidance for text-to-image diffusion models. ACM transactions on Graphics (TOG), Vol. 42, 4 (2023), 1-10."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01114"},{"key":"e_1_3_2_1_5_1","volume-title":"Ilvr: Conditioning method for denoising diffusion probabilistic models. arXiv preprint arXiv:2108.02938","author":"Choi Jooyoung","year":"2021","unstructured":"Jooyoung Choi, Sungwon Kim, Yonghyun Jeong, Youngjune Gwon, and Sungroh Yoon. 2021. Ilvr: Conditioning method for denoising diffusion probabilistic models. arXiv preprint arXiv:2108.02938 (2021)."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2023.02.021"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i3.27951"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"crossref","unstructured":"Xiefan Guo Jinlin Liu Miaomiao Cui Jiankai Li Hongyu Yang and Di Huang. 2024. InitNO: Boosting Text-to-Image Diffusion Models via Initial Noise Optimization. In CVPR.","DOI":"10.1109\/CVPR52733.2024.00896"},{"key":"e_1_3_2_1_10_1","volume-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium. Advances in neural information processing systems","author":"Heusel Martin","year":"2017","unstructured":"Martin Heusel, Hubert Ramsauer, Thomas Unterthiner, Bernhard Nessler, and Sepp Hochreiter. 2017. Gans trained by a two time-scale update rule converge to a local nash equilibrium. Advances in neural information processing systems, Vol. 30 (2017)."},{"key":"e_1_3_2_1_11_1","volume-title":"Denoising diffusion probabilistic models. Advances in neural information processing systems","author":"Ho Jonathan","year":"2020","unstructured":"Jonathan Ho, Ajay Jain, and Pieter Abbeel. 2020. Denoising diffusion probabilistic models. Advances in neural information processing systems, Vol. 33 (2020), 6840-6851."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00217"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73036-8_21"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00090"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00532"},{"key":"e_1_3_2_1_16_1","volume-title":"PrefPaint: Aligning Image Inpainting Diffusion Model with Human Preference. arXiv preprint arXiv:2410.21966","author":"Liu Kendong","year":"2024","unstructured":"Kendong Liu, Zhiyu Zhu, Chuanhao Li, Hui Liu, Huanqiang Zeng, and Junhui Hou. 2024. PrefPaint: Aligning Image Inpainting Diffusion Model with Human Preference. arXiv preprint arXiv:2410.21966 (2024)."},{"key":"e_1_3_2_1_17_1","volume-title":"Semantic-Driven Initial Image Construction for Guided Image Synthesis in Diffusion Model. arXiv preprint arXiv:2312.08872","author":"Mao Jiafeng","year":"2023","unstructured":"Jiafeng Mao, Xueting Wang, and Kiyoharu Aizawa. 2023. Semantic-Driven Initial Image Construction for Guided Image Synthesis in Diffusion Model. arXiv preprint arXiv:2312.08872 (2023)."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_2_1_19_1","first-page":"234","volume-title":"Munich","author":"Ronneberger Olaf","year":"2015","unstructured":"Olaf Ronneberger, Philipp Fischer, and Thomas Brox. 2015. U-net: Convolutional networks for biomedical image segmentation. In Medical image computing and computer-assisted intervention-MICCAI 2015: 18th international conference, Munich, Germany, October 5-9, 2015, proceedings, part III 18. Springer, 234-241."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3528233.3530757"},{"key":"e_1_3_2_1_21_1","volume-title":"Burcu Karagol Ayan, Tim Salimans, et al.","author":"Saharia Chitwan","year":"2022","unstructured":"Chitwan Saharia, William Chan, Saurabh Saxena, Lala Li, Jay Whang, Emily L Denton, Kamyar Ghasemipour, Raphael Gontijo Lopes, Burcu Karagol Ayan, Tim Salimans, et al., 2022b. Photorealistic text-to-image diffusion models with deep language understanding. Advances in neural information processing systems, Vol. 35 (2022), 36479-36494."},{"key":"e_1_3_2_1_22_1","volume-title":"Pixelcnn: Improving the pixelcnn with discretized logistic mixture likelihood and other modifications. arXiv preprint arXiv:1701.05517","author":"Salimans Tim","year":"2017","unstructured":"Tim Salimans, Andrej Karpathy, Xi Chen, and Diederik P Kingma. 2017. Pixelcnn: Improving the pixelcnn with discretized logistic mixture likelihood and other modifications. arXiv preprint arXiv:1701.05517 (2017)."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28270"},{"key":"e_1_3_2_1_24_1","volume-title":"Denoising diffusion implicit models. arXiv preprint arXiv:2010.02502","author":"Song Jiaming","year":"2020","unstructured":"Jiaming Song, Chenlin Meng, and Stefano Ermon. 2020. Denoising diffusion implicit models. arXiv preprint arXiv:2010.02502 (2020)."},{"key":"e_1_3_2_1_25_1","volume-title":"MVDiffusion: Enabling Holistic Multi-view Image Generation with Correspondence-Aware Diffusion. arXiv","author":"Tang Shitao","year":"2023","unstructured":"Shitao Tang, Fuyang Zhang, Jiacheng Chen, Peng Wang, and Yasutaka Furukawa. 2023. MVDiffusion: Enabling Holistic Multi-view Image Generation with Correspondence-Aware Diffusion. arXiv (2023)."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3658157"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00191"},{"key":"e_1_3_2_1_28_1","volume-title":"Image outpainting and harmonization using generative adversarial networks. arXiv preprint arXiv:1912.10960","author":"Hoorick Basile Van","year":"2019","unstructured":"Basile Van Hoorick. 2019. Image outpainting and harmonization using generative adversarial networks. arXiv preprint arXiv:1912.10960 (2019)."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00669"},{"key":"e_1_3_2_1_30_1","volume-title":"The Silent Prompt: Initial Noise as Implicit Guidance for Goal-Driven Image Generation. arXiv preprint arXiv:2412.05101","author":"Wang Ruoyu","year":"2024","unstructured":"Ruoyu Wang, Huayang Huang, Ye Zhu, Olga Russakovsky, and Yu Wu. 2024. The Silent Prompt: Initial Noise as Implicit Guidance for Goal-Driven Image Generation. arXiv preprint arXiv:2412.05101 (2024)."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3054477"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72646-0_22"},{"key":"e_1_3_2_1_33_1","volume-title":"Zeke Xie, Zhong Ji, Jungong Han, and Mingming Sun.","author":"Yang Jinze","year":"2024","unstructured":"Jinze Yang, Haoran Wang, Zining Zhu, Chenglong Liu, Meng Wymond Wu, Zeke Xie, Zhong Ji, Jungong Han, and Mingming Sun. 2024. VIP: Versatile Image Outpainting Empowered by Multimodal Large Language Model. arXiv preprint arXiv:2406.01059 (2024)."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.01066"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20050-2_10"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"e_1_3_2_1_38_1","unstructured":"Shaofeng Zhang Jinfa Huang Qiang Zhou Zhibin Wang Fan Wang Jiebo Luo and Junchi Yan. 2024. Continuous-Multiple Image Outpainting in One-Step via Positional Query and A Diffusion-based Approach. arXiv:2401.15652 [cs.CV]"},{"key":"e_1_3_2_1_39_1","volume-title":"Places: A 10 million Image Database for Scene Recognition","author":"Zhou Bolei","year":"2017","unstructured":"Bolei Zhou, Agata Lapedriza, Aditya Khosla, Aude Oliva, and Antonio Torralba. 2017. Places: A 10 million Image Database for Scene Recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence (2017)."},{"key":"e_1_3_2_1_40_1","volume-title":"Golden noise for diffusion models: A learning framework. arXiv preprint arXiv:2411.09502","author":"Zhou Zikai","year":"2024","unstructured":"Zikai Zhou, Shitong Shao, Lichen Bai, Zhiqiang Xu, Bo Han, and Zeke Xie. 2024. Golden noise for diffusion models: A learning framework. arXiv preprint arXiv:2411.09502 (2024)."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"crossref","unstructured":"Junhao Zhuang Yanhong Zeng Wenran Liu Chun Yuan and Kai Chen. 2023. A Task is Worth One Word: Learning with Task Prompts for High-Quality Versatile Image Inpainting. arXiv:2312.03594 [cs.CV]","DOI":"10.1007\/978-3-031-73636-0_12"}],"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\/3746027.3755278","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T19:45:51Z","timestamp":1765309551000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3755278"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":41,"alternative-id":["10.1145\/3746027.3755278","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3755278","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"}}]}}