{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T19:41:44Z","timestamp":1765309304256,"version":"3.46.0"},"publisher-location":"New York, NY, USA","reference-count":54,"publisher":"ACM","funder":[{"name":"Natural Science Foundation of China","award":["62271465"],"award-info":[{"award-number":["62271465"]}]},{"name":"Suzhou Basic Research Program","award":["SYG202338"],"award-info":[{"award-number":["SYG202338"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3754905","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T06:56:44Z","timestamp":1761375404000},"page":"9481-9490","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["LoCo: Training-Free Layout-to-Image Synthesis with Localized Constraints"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-0451-9902","authenticated-orcid":false,"given":"Peiang","family":"Zhao","sequence":"first","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8029-1498","authenticated-orcid":false,"given":"Han","family":"Li","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China and Technical University of Munich, Munich, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-8944-2312","authenticated-orcid":false,"given":"Ruiyang","family":"Jin","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6881-4444","authenticated-orcid":false,"given":"S. Kevin","family":"Zhou","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01762"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01834"},{"key":"e_1_3_2_1_3_1","unstructured":"Yogesh Balaji Seungjun Nah Xun Huang Arash Vahdat Jiaming Song Karsten Kreis Miika Aittala Timo Aila Samuli Laine Bryan Catanzaro et al. 2022. ediffi: Text-to-image diffusion models with an ensemble of expert denoisers. arXiv preprint arXiv:2211.01324 (2022)."},{"key":"e_1_3_2_1_4_1","volume-title":"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. International conference on machine learning (2023)."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3592116"},{"key":"e_1_3_2_1_6_1","volume-title":"Pixart-\u03b1: Fast training of diffusion transformer for photorealistic text-to-image synthesis. arXiv preprint arXiv:2310.00426","author":"Chen Junsong","year":"2023","unstructured":"Junsong Chen, Jincheng Yu, Chongjian Ge, Lewei Yao, Enze Xie, Yue Wu, Zhongdao Wang, James Kwok, Ping Luo, Huchuan Lu, et al., 2023. Pixart-\u03b1: Fast training of diffusion transformer for photorealistic text-to-image synthesis. arXiv preprint arXiv:2310.00426 (2023)."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00526"},{"key":"e_1_3_2_1_8_1","volume-title":"HiCo: Hierarchical Controllable Diffusion Model for Layout-to-image Generation. arXiv preprint arXiv:2410.14324","author":"Cheng Bo","year":"2024","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. arXiv preprint arXiv:2410.14324 (2024)."},{"key":"e_1_3_2_1_9_1","volume-title":"Layoutdiffuse: Adapting foundational diffusion models for layout-to-image generation. arXiv preprint arXiv:2302.08908","author":"Cheng Jiaxin","year":"2023","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. arXiv preprint arXiv:2302.08908 (2023)."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00207"},{"key":"e_1_3_2_1_11_1","volume-title":"Xin Eric Wang, and William Yang Wang","author":"Feng Weixi","year":"2022","unstructured":"Weixi Feng, Xuehai He, Tsu-Jui Fu, Varun Jampani, Arjun Akula, Pradyumna Narayana, Sugato Basu, Xin Eric Wang, and William Yang Wang. 2022. Training-free structured diffusion guidance for compositional text-to-image synthesis. arXiv preprint arXiv:2212.05032 (2022)."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19784-0_6"},{"key":"e_1_3_2_1_13_1","volume-title":"Locate, Rectify: A Training-Free Layout Calibration System for Text-to-Image Generation. arXiv preprint arXiv:2311.15773","author":"Gong Biao","year":"2023","unstructured":"Biao Gong, Siteng Huang, Yutong Feng, Shiwei Zhang, Yuyuan Li, and Yu Liu. 2023. Check, Locate, Rectify: A Training-Free Layout Calibration System for Text-to-Image Generation. arXiv preprint arXiv:2311.15773 (2023)."},{"key":"e_1_3_2_1_14_1","volume-title":"Localized Text-to-Image Generation for Free via Cross Attention Control. arXiv preprint arXiv:2306.14636","author":"He Yutong","year":"2023","unstructured":"Yutong He, Ruslan Salakhutdinov, and J Zico Kolter. 2023. Localized Text-to-Image Generation for Free via Cross Attention Control. arXiv preprint arXiv:2306.14636 (2023)."},{"key":"e_1_3_2_1_15_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_1_16_1","volume-title":"Classifier-free diffusion guidance. arXiv preprint arXiv:2207.12598","author":"Ho Jonathan","year":"2022","unstructured":"Jonathan Ho and Tim Salimans. 2022. Classifier-free diffusion guidance. arXiv preprint arXiv:2207.12598 (2022)."},{"key":"e_1_3_2_1_17_1","volume-title":"Yap-Peng Tan, and Weipeng Hu.","author":"Hoe Jiun Tian","year":"2023","unstructured":"Jiun Tian Hoe, Xudong Jiang, Chee Seng Chan, Yap-Peng Tan, and Weipeng Hu. 2023. InteractDiffusion: Interaction Control in Text-to-Image Diffusion Models. arXiv preprint arXiv:2312.05849 (2023)."},{"key":"e_1_3_2_1_18_1","volume-title":"Counting Guidance for High Fidelity Text-to-Image Synthesis. arXiv preprint arXiv:2306.17567","author":"Kang Wonjun","year":"2023","unstructured":"Wonjun Kang, Kevin Galim, and Hyung Il Koo. 2023. Counting Guidance for High Fidelity Text-to-Image Synthesis. arXiv preprint arXiv:2306.17567 (2023)."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00708"},{"key":"e_1_3_2_1_20_1","volume-title":"GrounDiT: Grounding Diffusion Transformers via Noisy Patch Transplantation. arXiv preprint arXiv:2410.20474","author":"Lee Phillip Y","year":"2024","unstructured":"Phillip Y Lee, Taehoon Yoon, and Minhyuk Sung. 2024. GrounDiT: Grounding Diffusion Transformers via Noisy Patch Transplantation. arXiv preprint arXiv:2410.20474 (2024)."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02156"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01356"},{"key":"e_1_3_2_1_23_1","unstructured":"Zhimin Li Jianwei Zhang Qin Lin Jiangfeng Xiong Yanxin Long Xinchi Deng Yingfang Zhang Xingchao Liu Minbin Huang Zedong Xiao et al. 2024. Hunyuan-DiT: A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understanding. arXiv preprint arXiv:2405.08748 (2024)."},{"key":"e_1_3_2_1_24_1","volume-title":"Training-free Composite Scene Generation for Layout-to-Image Synthesis. arXiv preprint arXiv:2407.13609","author":"Liu Jiaqi","year":"2024","unstructured":"Jiaqi Liu, Tao Huang, and Chang Xu. 2024. Training-free Composite Scene Generation for Layout-to-Image Synthesis. arXiv preprint arXiv:2407.13609 (2024)."},{"key":"e_1_3_2_1_25_1","volume-title":"Cones 2: Customizable Image Synthesis with Multiple Subjects. arXiv preprint arXiv:2305.19327","author":"Liu Zhiheng","year":"2023","unstructured":"Zhiheng Liu, Yifei Zhang, Yujun Shen, Kecheng Zheng, Kai Zhu, Ruili Feng, Yu Liu, Deli Zhao, Jingren Zhou, and Yang Cao. 2023. Cones 2: Customizable Image Synthesis with Multiple Subjects. arXiv preprint arXiv:2305.19327 (2023)."},{"key":"e_1_3_2_1_26_1","volume-title":"Diffusionseg: Adapting diffusion towards unsupervised object discovery. arXiv preprint arXiv:2303.09813","author":"Ma Chaofan","year":"2023","unstructured":"Chaofan Ma, Yuhuan Yang, Chen Ju, Fei Zhang, Jinxiang Liu, Yu Wang, Ya Zhang, and Yanfeng Wang. 2023b. Diffusionseg: Adapting diffusion towards unsupervised object discovery. arXiv preprint arXiv:2303.09813 (2023)."},{"key":"e_1_3_2_1_27_1","volume-title":"Directed diffusion: Direct control of object placement through attention guidance. arXiv preprint arXiv:2302.13153","author":"Kurt Ma Wan-Duo","year":"2023","unstructured":"Wan-Duo Kurt Ma, JP Lewis, W Bastiaan Kleijn, and Thomas Leung. 2023a. Directed diffusion: Direct control of object placement through attention guidance. arXiv preprint arXiv:2302.13153 (2023)."},{"key":"e_1_3_2_1_28_1","volume-title":"T2i-adapter: Learning adapters to dig out more controllable ability for text-to-image diffusion models. arXiv preprint arXiv:2302.08453","author":"Mou Chong","year":"2023","unstructured":"Chong Mou, Xintao Wang, Liangbin Xie, Yanze Wu, Jian Zhang, Zhongang Qi, Ying Shan, and Xiaohu Qie. 2023. T2i-adapter: Learning adapters to dig out more controllable ability for text-to-image diffusion models. arXiv preprint arXiv:2302.08453 (2023)."},{"key":"e_1_3_2_1_29_1","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Nguyen Quang","year":"2024","unstructured":"Quang Nguyen, Truong Vu, Anh Tran, and Khoi Nguyen. 2024. Dataset diffusion: Diffusion-based synthetic data generation for pixel-level semantic segmentation. Advances in Neural Information Processing Systems, Vol. 36 (2024)."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"e_1_3_2_1_31_1","volume-title":"Grounded Text-to-Image Synthesis with Attention Refocusing. arXiv preprint arXiv:2306.05427","author":"Phung Quynh","year":"2023","unstructured":"Quynh Phung, Songwei Ge, and Jia-Bin Huang. 2023. Grounded Text-to-Image Synthesis with Attention Refocusing. arXiv preprint arXiv:2306.05427 (2023)."},{"key":"e_1_3_2_1_32_1","volume-title":"Sdxl: improving latent diffusion models for high-resolution image synthesis. arXiv preprint arXiv: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 preprint arXiv:2307.01952 (2023)."},{"key":"e_1_3_2_1_33_1","volume-title":"International conference on machine learning. PMLR, 8748-8763","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, et al., 2021. Learning transferable visual models from natural language supervision. In International conference on machine learning. PMLR, 8748-8763."},{"key":"e_1_3_2_1_34_1","volume-title":"Hierarchical text-conditional image generation with clip latents. arXiv preprint arXiv:2204.06125","author":"Ramesh Aditya","year":"2022","unstructured":"Aditya Ramesh, Prafulla Dhariwal, Alex Nichol, Casey Chu, and Mark Chen. 2022. Hierarchical text-conditional image generation with clip latents. arXiv preprint arXiv:2204.06125, Vol. 1, 2 (2022), 3."},{"key":"e_1_3_2_1_35_1","volume-title":"ConceptLab: Creative Generation using Diffusion Prior Constraints. arXiv preprint arXiv:2308.02669","author":"Richardson Elad","year":"2023","unstructured":"Elad Richardson, Kfir Goldberg, Yuval Alaluf, and Daniel Cohen-Or. 2023. ConceptLab: Creative Generation using Diffusion Prior Constraints. arXiv preprint arXiv:2308.02669 (2023)."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_2_1_37_1","first-page":"36479","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","volume":"35","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., 2022. Photorealistic text-to-image diffusion models with deep language understanding. Advances in Neural Information Processing Systems, Vol. 35 (2022), 36479-36494.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_38_1","volume-title":"Spatial-Aware Latent Initialization for Controllable Image Generation. arXiv preprint arXiv:2401.16157","author":"Sun Wenqiang","year":"2024","unstructured":"Wenqiang Sun, Teng Li, Zehong Lin, and Jun Zhang. 2024. Spatial-Aware Latent Initialization for Controllable Image Generation. arXiv preprint arXiv:2401.16157 (2024)."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3078577"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3613806"},{"key":"e_1_3_2_1_41_1","volume-title":"Compositional text-to-image synthesis with attention map control of diffusion models. arXiv preprint arXiv:2305.13921","author":"Wang Ruichen","year":"2023","unstructured":"Ruichen Wang, Zekang Chen, Chen Chen, Jian Ma, Haonan Lu, and Xiaodong Lin. 2023. Compositional text-to-image synthesis with attention map control of diffusion models. arXiv preprint arXiv:2305.13921 (2023)."},{"key":"e_1_3_2_1_42_1","volume-title":"Semantic image synthesis via diffusion models. arXiv preprint arXiv:2207.00050","author":"Wang Weilun","year":"2022","unstructured":"Weilun Wang, Jianmin Bao, Wengang Zhou, Dongdong Chen, Dong Chen, Lu Yuan, and Houqiang Li. 2022. Semantic image synthesis via diffusion models. arXiv preprint arXiv:2207.00050 (2022)."},{"key":"e_1_3_2_1_43_1","volume-title":"Rohit Girdhar, and Ishan Misra.","author":"Wang Xudong","year":"2024","unstructured":"Xudong Wang, Trevor Darrell, Sai Saketh Rambhatla, Rohit Girdhar, and Ishan Misra. 2024. InstanceDiffusion: Instance-level Control for Image Generation. arXiv preprint arXiv:2402.03290 (2024)."},{"key":"e_1_3_2_1_44_1","volume-title":"Region and Boundary Aware Zero-shot Grounded Text-to-image Generation. arXiv preprint arXiv:2310.08872","author":"Xiao Jiayu","year":"2023","unstructured":"Jiayu Xiao, Liang Li, Henglei Lv, Shuhui Wang, and Qingming Huang. 2023. R&B: Region and Boundary Aware Zero-shot Grounded Text-to-image Generation. arXiv preprint arXiv:2310.08872 (2023)."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00685"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01370"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02072"},{"key":"e_1_3_2_1_48_1","volume-title":"Cogvideox: Text-to-video diffusion models with an expert transformer. arXiv preprint arXiv:2408.06072","author":"Yang Zhuoyi","year":"2024","unstructured":"Zhuoyi Yang, Jiayan Teng, Wendi Zheng, Ming Ding, Shiyu Huang, Jiazheng Xu, Yuanming Yang, Wenyi Hong, Xiaohan Zhang, Guanyu Feng, et al., 2024. Cogvideox: Text-to-video diffusion models with an expert transformer. arXiv preprint arXiv:2408.06072 (2024)."},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01369"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02152"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00878"},{"key":"e_1_3_2_1_53_1","volume-title":"MIGC: Multi-Instance Generation Controller for Text-to-Image Synthesis. arXiv preprint arXiv:2402.05408","author":"Zhou Dewei","year":"2024","unstructured":"Dewei Zhou, You Li, Fan Ma, Zongxin Yang, and Yi Yang. 2024. MIGC: Multi-Instance Generation Controller for Text-to-Image Synthesis. arXiv preprint arXiv:2402.05408 (2024)."},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00742"}],"event":{"name":"MM '25: The 33rd ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Dublin Ireland","acronym":"MM '25"},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3754905","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T19:39:15Z","timestamp":1765309155000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3754905"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":54,"alternative-id":["10.1145\/3746027.3754905","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3754905","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"}}]}}