{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T19:47:11Z","timestamp":1765309631558,"version":"3.46.0"},"publisher-location":"New York, NY, USA","reference-count":42,"publisher":"ACM","funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62232014,62272377"],"award-info":[{"award-number":["62232014,62272377"]}],"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\/3746027.3754818","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T06:56:44Z","timestamp":1761375404000},"page":"5365-5374","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Illustration Layout Generation for Slide Enhancement with Pixel-based Diffusion Model"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0133-9228","authenticated-orcid":false,"given":"Zhaoyun","family":"Jiang","sequence":"first","affiliation":[{"name":"Xi'an Jiaotong University, Xi'an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-3240-5921","authenticated-orcid":false,"given":"Jiaqi","family":"Guo","sequence":"additional","affiliation":[{"name":"Microsoft Corporation, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-6455-6227","authenticated-orcid":false,"given":"Shakie","family":"Liu","sequence":"additional","affiliation":[{"name":"Microsoft Corporation, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-8268-8010","authenticated-orcid":false,"given":"Chao","family":"Han","sequence":"additional","affiliation":[{"name":"Microsoft Corporation, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7600-0934","authenticated-orcid":false,"given":"Ting","family":"Liu","sequence":"additional","affiliation":[{"name":"Xi'an Jiaotong University, Xi'an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8496-033X","authenticated-orcid":false,"given":"Jian-Guang","family":"Lou","sequence":"additional","affiliation":[{"name":"Microsoft Corporation, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9230-2799","authenticated-orcid":false,"given":"Dongmei","family":"Zhang","sequence":"additional","affiliation":[{"name":"Microsoft Corporation, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"2025. Canva. https:\/\/www.canva.com."},{"key":"e_1_3_2_1_2_1","unstructured":"Yutao Cheng Zhao Zhang Maoke Yang Hui Nie Chunyuan Li Xinglong Wu and Jie Shao. 2024. Graphic Design with Large Multimodal Model. arXiv:2404.14368 [cs.CV] https:\/\/arxiv.org\/abs\/2404.14368"},{"key":"e_1_3_2_1_3_1","volume-title":"The Eleventh International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=NAQvF08TcyG","author":"Gal Rinon","year":"2023","unstructured":"Rinon Gal, Yuval Alaluf, Yuval Atzmon, Or Patashnik, Amit Haim Bermano, Gal Chechik, and Daniel Cohen-or. 2023. An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion. In The Eleventh International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=NAQvF08TcyG"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00221"},{"key":"e_1_3_2_1_5_1","volume-title":"Prompt-to-Prompt Image Editing with Cross-Attention Control. In The Eleventh International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=_CDixzkzeyb","author":"Hertz Amir","year":"2023","unstructured":"Amir Hertz, Ron Mokady, Jay Tenenbaum, Kfir Aberman, Yael Pritch, and Daniel Cohen-or. 2023. Prompt-to-Prompt Image Editing with Cross-Attention Control. In The Eleventh International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=_CDixzkzeyb"},{"key":"e_1_3_2_1_6_1","volume-title":"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. In Advances in Neural Information Processing Systems, I. Guyon, U. Von Luxburg, S. Bengio, H.Wallach, R. Fergus, S. Vishwanathan, and R. Garnett (Eds.), Vol. 30. Curran Associates, Inc. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2017\/file\/8a1d694707eb0fefe65871369074926d-Paper.pdf"},{"key":"e_1_3_2_1_7_1","first-page":"6840","volume-title":"Lin (Eds.)","volume":"33","author":"Ho Jonathan","year":"2020","unstructured":"Jonathan Ho, Ajay Jain, and Pieter Abbeel. 2020. Denoising Diffusion Probabilistic Models. In Advances in Neural Information Processing Systems, H. Larochelle, M. Ranzato, R. Hadsell, M.F. Balcan, and H. Lin (Eds.), Vol. 33. Curran Associates, Inc., 6840-6851. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2020\/file\/4c5bcfec8584af0d967f1ab10179ca4b-Paper.pdf"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00015"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00583"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01373"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00190"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"crossref","unstructured":"Juil Koo Chanho Park and Minhyuk Sung. 2024. Posterior Distillation Sampling. In CVPR.","DOI":"10.1109\/CVPR52733.2024.01268"},{"key":"e_1_3_2_1_13_1","unstructured":"Black Forest Labs. 2024. FLUX. https:\/\/github.com\/black-forest-labs\/flux."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.353"},{"key":"e_1_3_2_1_15_1","first-page":"43852","volume-title":"Levine (Eds.)","volume":"36","author":"Lin Jiawei","year":"2023","unstructured":"Jiawei Lin, Jiaqi Guo, Shizhao Sun, Zijiang Yang, Jian-Guang Lou, and Dongmei Zhang. 2023. LayoutPrompter: Awaken the Design Ability of Large Language Models. In Advances in Neural Information Processing Systems, A. Oh, T. Naumann, A. Globerson, K. Saenko, M. Hardt, and S. Levine (Eds.), Vol. 36. Curran Associates, Inc., 43852-43879. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2023\/file\/88a129e44f25a571ae8b838057c46855-Paper-Conference.pdf"},{"key":"e_1_3_2_1_16_1","unstructured":"Jiawei Lin Shizhao Sun Danqing Huang Ting Liu Ji Li and Jiang Bian. 2024. From Elements to Design: A Layered Approach for Automatic Graphic Design Composition. arXiv:2412.19712 [cs.CV] https:\/\/arxiv.org\/abs\/2412.19712"},{"key":"e_1_3_2_1_17_1","unstructured":"Shilong Liu Zhaoyang Zeng Tianhe Ren Feng Li Hao Zhang Jie Yang Chunyuan Li Jianwei Yang Hang Su Jun Zhu et al. 2023. Grounding dino: Marrying dino with grounded pre-training for open-set object detection. arXiv preprint arXiv:2303.05499 (2023)."},{"key":"e_1_3_2_1_18_1","unstructured":"OpenCV. 2025. Contour Features. https:\/\/docs.opencv.org\/3.4\/dd\/d49\/tutorial_py_contour_features.html."},{"key":"e_1_3_2_1_19_1","volume-title":"The Eleventh International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=FjNys5c7VyY","author":"Poole Ben","year":"2023","unstructured":"Ben Poole, Ajay Jain, Jonathan T. Barron, and Ben Mildenhall. 2023. DreamFusion: Text-to-3D using 2D Diffusion. In The Eleventh International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=FjNys5c7VyY"},{"key":"e_1_3_2_1_20_1","volume-title":"Proceedings of the 38th International Conference on Machine Learning (Proceedings of Machine Learning Research","volume":"8831","author":"Ramesh Aditya","year":"2021","unstructured":"Aditya Ramesh, Mikhail Pavlov, Gabriel Goh, Scott Gray, Chelsea Voss, Alec Radford, Mark Chen, and Ilya Sutskever. 2021. Zero-Shot Text-to-Image Generation. In Proceedings of the 38th International Conference on Machine Learning (Proceedings of Machine Learning Research, Vol. 139), Marina Meila and Tong Zhang (Eds.). PMLR, 8821-8831. https:\/\/proceedings.mlr.press\/v139\/ramesh21a.html"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"e_1_3_2_1_23_1","first-page":"36479","volume-title":"Oh (Eds.)","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, Jonathan Ho, David J Fleet, and Mohammad Norouzi. 2022. Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding. In Advances in Neural Information Processing Systems, S. Koyejo, S. Mohamed, A. Agarwal, D. Belgrave, K. Cho, and A. Oh (Eds.), Vol. 35. Curran Associates, Inc., 36479-36494. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2022\/file\/ec795aeadae0b7d230fa35cbaf04c041-Paper-Conference.pdf"},{"key":"e_1_3_2_1_24_1","unstructured":"Christoph Schuhmann. 2022. Improved aesthetic predictor. https:\/\/github.com\/christophschuhmann\/improved-aesthetic-predictor."},{"key":"e_1_3_2_1_25_1","volume-title":"Proceedings of the 36th International Conference on Neural Information Processing Systems","author":"Schuhmann Christoph","year":"2022","unstructured":"Christoph Schuhmann, Romain Beaumont, Richard Vencu, Cade Gordon, Ross Wightman, Mehdi Cherti, Theo Coombes, Aarush Katta, Clayton Mullis, Mitchell Wortsman, Patrick Schramowski, Srivatsa Kundurthy, Katherine Crowson, Ludwig Schmidt, Robert Kaczmarczyk, and Jenia Jitsev. 2022. LAION-5B: an open large-scale dataset for training next generation image-text models. In Proceedings of the 36th International Conference on Neural Information Processing Systems (New Orleans, LA, USA) (NIPS '22). Curran Associates Inc., Red Hook, NY, USA, Article 1833, 17 pages."},{"key":"e_1_3_2_1_26_1","volume-title":"Computer Vision - ECCV","author":"Seol Jaejung","year":"2024","unstructured":"Jaejung Seol, Seojun Kim, and Jaejun Yoo. 2025. PosterLlama: Bridging Design Ability of Language Model to Content-Aware Layout Generation. In Computer Vision - ECCV 2024, Ale\u0161 Leonardis, Elisa Ricci, Stefan Roth, Olga Russakovsky, Torsten Sattler, and G\u00fcl Varol (Eds.). Springer Nature Switzerland, Cham, 451-468."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00881"},{"key":"e_1_3_2_1_28_1","volume-title":"Garnett (Eds.)","volume":"32","author":"Song Yang","year":"2019","unstructured":"Yang Song and Stefano Ermon. 2019. Generative Modeling by Estimating Gradients of the Data Distribution. In Advances in Neural Information Processing Systems, H. Wallach, H. Larochelle, A. Beygelzimer, F. d'Alch\u00e9-Buc, E. Fox, and R. Garnett (Eds.), Vol. 32. Curran Associates, Inc. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2019\/file\/3001ef257407d5a371a96dcd947c7d93-Paper.pdf"},{"key":"e_1_3_2_1_29_1","volume-title":"International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=PxTIG12RRHS","author":"Song Yang","year":"2021","unstructured":"Yang Song, Jascha Sohl-Dickstein, Diederik P Kingma, Abhishek Kumar, Stefano Ermon, and Ben Poole. 2021. Score-Based Generative Modeling through Stochastic Differential Equations. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=PxTIG12RRHS"},{"key":"e_1_3_2_1_30_1","unstructured":"StabilityAI. 2023. If by deepfloyd lab at stabilityai. https:\/\/github.com\/deepfloyd\/IF."},{"key":"e_1_3_2_1_31_1","unstructured":"Qwen Team. 2024. Qwen2.5: A Party of Foundation Models. https:\/\/qwenlm.github.io\/blog\/qwen2.5\/"},{"key":"e_1_3_2_1_32_1","volume-title":"Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution. arXiv preprint arXiv:2409.12191","author":"Wang Peng","year":"2024","unstructured":"Peng Wang, Shuai Bai, Sinan Tan, Shijie Wang, Zhihao Fan, Jinze Bai, Keqin Chen, Xuejing Liu, Jialin Wang, Wenbin Ge, Yang Fan, Kai Dang, Mengfei Du, Xuancheng Ren, Rui Men, Dayiheng Liu, Chang Zhou, Jingren Zhou, and Junyang Lin. 2024. Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution. arXiv preprint arXiv:2409.12191 (2024)."},{"key":"e_1_3_2_1_33_1","volume-title":"Advances in Neural Information Processing Systems","author":"Wang Zhengyi","year":"2023","unstructured":"Zhengyi Wang, Cheng Lu, Yikai Wang, Fan Bao, Chongxuan LI, Hang Su, and Jun Zhu. 2023. ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillation. In Advances in Neural Information Processing Systems, A. Oh, T. Naumann, A. Globerson, K. Saenko, M. Hardt, and S. Levine (Eds.), Vol. 36. Curran Associates, Inc., 8406-8441. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2023\/file\/1a87980b9853e84dfb295855b425c262-Paper-Conference.pdf"},{"key":"e_1_3_2_1_34_1","volume-title":"International Journal of Computer Vision","author":"Wu Ronghuan","year":"2024","unstructured":"Ronghuan Wu, Wanchao Su, Kede Ma, and Jing Liao. 2024. AniClipart: Clipart animation with text-to-video priors. International Journal of Computer Vision (2024), 1-17."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00200"},{"key":"e_1_3_2_1_36_1","volume-title":"Thirty-seventh Conference on Neural Information Processing Systems. https:\/\/openreview.net\/forum?id=CY1xatvEQj","author":"Xing XiMing","year":"2023","unstructured":"XiMing Xing, Chuang Wang, Haitao Zhou, Jing Zhang, Qian Yu, and Dong Xu. 2023. DiffSketcher: Text Guided Vector Sketch Synthesis through Latent Diffusion Models. In Thirty-seventh Conference on Neural Information Processing Systems. https:\/\/openreview.net\/forum?id=CY1xatvEQj"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00435"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00975"},{"key":"e_1_3_2_1_39_1","unstructured":"Tao Yang Yingmin Luo Zhongang Qi Yang Wu Ying Shan and Chang Wen Chen. 2024. PosterLLaVa: Constructing a Unified Multi-modal Layout Generator with LLM. arXiv:2406.02884 [cs.CV] https:\/\/arxiv.org\/abs\/2406.02884"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/2818709"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"crossref","unstructured":"Min Zhou Chenchen Xu Ye Ma Tiezheng Ge Yuning Jiang and Weiwei Xu. 2022. Composition-aware Graphic Layout GAN for Visual-textual Presentation Designs. arXiv:2205.00303 [cs.CV] https:\/\/arxiv.org\/abs\/2205.00303","DOI":"10.24963\/ijcai.2022\/692"}],"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\/3746027.3754818","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T19:44:55Z","timestamp":1765309495000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3754818"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":42,"alternative-id":["10.1145\/3746027.3754818","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3754818","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"}}]}}