{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,23]],"date-time":"2026-04-23T07:58:44Z","timestamp":1776931124320,"version":"3.51.2"},"publisher-location":"New York, NY, USA","reference-count":50,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,12,15]]},"DOI":"10.1145\/3757377.3763944","type":"proceedings-article","created":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T16:27:29Z","timestamp":1765211249000},"page":"1-12","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["AGSwap: Overcoming Category Boundaries in Object Fusion via Adaptive Group Swapping"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3328-1713","authenticated-orcid":false,"given":"Zedong","family":"Zhang","sequence":"first","affiliation":[{"name":"Nanjing University of Science and Technology, Nanjing, Jiangsu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4665-6852","authenticated-orcid":false,"given":"Ying","family":"Tai","sequence":"additional","affiliation":[{"name":"Nanjing University, Nanjing, Jiangsu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0968-8556","authenticated-orcid":false,"given":"Jianjun","family":"Qian","sequence":"additional","affiliation":[{"name":"Nanjing University of Science and Technology, Nanjing, Jiangsu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4800-832X","authenticated-orcid":false,"given":"Jian","family":"Yang","sequence":"additional","affiliation":[{"name":"Nanjing University of Science and Technology, Nanjing, Jiangsu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3716-671X","authenticated-orcid":false,"given":"Jun","family":"Li","sequence":"additional","affiliation":[{"name":"Nanjing University of Science and Technology, Nanjing, Jiangsu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,12,14]]},"reference":[{"key":"e_1_3_3_2_2_1","unstructured":"BRIA AI. 2024. BRIA Background Removal v2.0. https:\/\/huggingface.co\/briaai\/RMBG-2.0."},{"key":"e_1_3_3_2_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657527"},{"key":"e_1_3_3_2_4_1","doi-asserted-by":"crossref","unstructured":"Margaret\u00a0A Boden. 1998. Creativity and artificial intelligence. Artificial intelligence 103 1-2 (1998) 347\u2013356.","DOI":"10.1016\/S0004-3702(98)00055-1"},{"key":"e_1_3_3_2_5_1","doi-asserted-by":"publisher","DOI":"10.5555\/940309"},{"key":"e_1_3_3_2_6_1","first-page":"4055","volume-title":"Proceedings of the International Conference on Machine Learning (ICML)","author":"Chang Huiwen","year":"2023","unstructured":"Huiwen Chang, Han Zhang, Jarred Barber, Aaron Maschinot, Jose Lezama, Lu Jiang, Ming-Hsuan Yang, Kevin\u00a0Patrick Murphy, William\u00a0T Freeman, Michael Rubinstein, et\u00a0al. 2023. Muse: Text-To-Image Generation via Masked Generative Transformers. In Proceedings of the International Conference on Machine Learning (ICML). PMLR, 4055\u20134075."},{"key":"e_1_3_3_2_7_1","doi-asserted-by":"crossref","unstructured":"Haibo Chen Zhoujie Wang Lei Zhao Jun Li and Jian Yang. 2025a. Trtst: Arbitrary high-quality text-guided style transfer with transformers. IEEE Transactions on Image Processing (2025).","DOI":"10.1109\/TIP.2025.3530822"},{"key":"e_1_3_3_2_8_1","doi-asserted-by":"crossref","unstructured":"Haibo Chen Zhiwen Zuo Lei Zhao Jun Li and Jian Yang. 2025b. ConceptCraft: One-Shot Personalized Text-to-Image Generation via Object-Background Disentanglement. IEEE Transactions on Circuits and Systems for Video Technology (2025).","DOI":"10.1109\/TCSVT.2025.3596242"},{"key":"e_1_3_3_2_9_1","doi-asserted-by":"crossref","unstructured":"Florinel-Alin Croitoru Vlad Hondru Radu\u00a0Tudor Ionescu and Mubarak Shah. 2023. Diffusion models in vision: A survey. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) 45 9 (2023) 10850\u201310869.","DOI":"10.1109\/TPAMI.2023.3261988"},{"key":"e_1_3_3_2_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_3_2_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3680528.3687612"},{"key":"e_1_3_3_2_12_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-90-481-8847-5_10"},{"key":"e_1_3_3_2_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01719"},{"key":"e_1_3_3_2_14_1","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR)","author":"Gal Rinon","year":"2024","unstructured":"Rinon Gal, Yuval Alaluf, Yuval Atzmon, Or Patashnik, Amit\u00a0Haim Bermano, Gal Chechik, and Daniel Cohen-or. 2024. An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion. In Proceedings of the International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_3_2_15_1","doi-asserted-by":"crossref","unstructured":"Xiang Gao Shuai Yang and Jiaying Liu. 2025. PTDiffusion: Free Lunch for Generating Optical Illusion Hidden Pictures with Phase-Transferred Diffusion Model. arXiv:https:\/\/arXiv.org\/abs\/2503.06186 (2025).","DOI":"10.1109\/CVPR52734.2025.01700"},{"key":"e_1_3_3_2_16_1","first-page":"366","volume-title":"Proceedings of the European Conference on Computer Vision (ECCV)","author":"Geng Daniel","year":"2024","unstructured":"Daniel Geng, Inbum Park, and Andrew Owens. 2024. Factorized diffusion: Perceptual illusions by noise decomposition. In Proceedings of the European Conference on Computer Vision (ECCV). 366\u2013384."},{"key":"e_1_3_3_2_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00822"},{"key":"e_1_3_3_2_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02664"},{"key":"e_1_3_3_2_19_1","unstructured":"Jonathan Ho Ajay Jain and Pieter Abbeel. 2020. Denoising Diffusion Probabilistic Models. Proceedings of the Advances in Neural Information Processing Systems (NeurIPS) 33 (2020) 6840\u20136851."},{"key":"e_1_3_3_2_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01185"},{"key":"e_1_3_3_2_21_1","unstructured":"Aaron Hurst Adam Lerer Adam\u00a0P Goucher Adam Perelman Aditya Ramesh Aidan Clark AJ Ostrow Akila Welihinda Alan Hayes Alec Radford et\u00a0al. 2024. Gpt-4o system card. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2410.21276 (2024)."},{"key":"e_1_3_3_2_22_1","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Ju Xuan","year":"2023","unstructured":"Xuan Ju, Ailing Zeng, Yuxuan Bian, Shaoteng Liu, and Qiang Xu. 2023. PnP Inversion: Boosting Diffusion-based Editing with 3 Lines of Code. In Proceedings of the International Conference on Learning Representations."},{"key":"e_1_3_3_2_23_1","unstructured":"Alex Krizhevsky Geoffrey Hinton et\u00a0al. 2009. Learning multiple layers of features from tiny images. (2009)."},{"key":"e_1_3_3_2_24_1","unstructured":"Vladimir Kulikov Matan Kleiner Inbar Huberman-Spiegelglas and Tomer Michaeli. 2024. FlowEdit: Inversion-Free Text-Based Editing Using Pre-Trained Flow Models. arXiv:https:\/\/arXiv.org\/abs\/2412.08629 (2024)."},{"key":"e_1_3_3_2_25_1","unstructured":"Black\u00a0Forest Labs. 2025. FLUX.1 [schnell]. https:\/\/huggingface.co\/black-forest-labs\/FLUX.1-schnell."},{"key":"e_1_3_3_2_26_1","volume-title":"Proceedings of the European Conference on Computer Vision (ECCV)","author":"Li Jun","year":"2024","unstructured":"Jun Li, Zedong Zhang, and Jian Yang. 2024. TP2O: Creative Text Pair-to-Object Generation using Balance Swap-Sampling. In Proceedings of the European Conference on Computer Vision (ECCV)."},{"key":"e_1_3_3_2_27_1","doi-asserted-by":"crossref","unstructured":"Shimin Li Zedong Zhang Gan Sun Li-Wei\u00a0H Lehman Jian Yang and Jun Li. 2025b. Creative Style Transfer for Image Stylization via Learning Neural Permutation. Knowledge-Based Systems (2025) 114368.","DOI":"10.1016\/j.knosys.2025.114368"},{"key":"e_1_3_3_2_28_1","unstructured":"Yanfeng Li Kahou Chan Yue Sun Chantong Lam Tong Tong Zitong Yu Keren Fu Xiaohong Liu and Tao Tan. 2025a. MoEdit: On Learning Quantity Perception for Multi-object Image Editing. arXiv:https:\/\/arXiv.org\/abs\/2503.10112 (2025)."},{"key":"e_1_3_3_2_29_1","unstructured":"Jun\u00a0Hao Liew Hanshu Yan Daquan Zhou and Jiashi Feng. 2022. Magicmix: Semantic mixing with diffusion models. arXiv:https:\/\/arXiv.org\/abs\/2210.16056 (2022)."},{"key":"e_1_3_3_2_30_1","first-page":"366","volume-title":"European Conference on Computer Vision(ECCV)","author":"Lin Zhiqiu","year":"2024","unstructured":"Zhiqiu Lin, Deepak Pathak, Baiqi Li, Jiayao Li, Xide Xia, Graham Neubig, Pengchuan Zhang, and Deva Ramanan. 2024. Evaluating text-to-visual generation with image-to-text generation. In European Conference on Computer Vision(ECCV). Springer, 366\u2013384."},{"key":"e_1_3_3_2_31_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19790-1_26"},{"key":"e_1_3_3_2_32_1","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR)","author":"Luo Simian","year":"2024","unstructured":"Simian Luo, Ming Tan, Chenlin Wang, Di Huang, Xi Peng, et\u00a0al. 2024. Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference. In Proceedings of the International Conference on Learning Representations (ICLR). https:\/\/arxiv.org\/abs\/2303.01469"},{"key":"e_1_3_3_2_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00585"},{"key":"e_1_3_3_2_34_1","first-page":"420","volume-title":"Proceedings of the European Conference on Computer Vision","author":"Ng Kam\u00a0Woh","year":"2024","unstructured":"Kam\u00a0Woh Ng, Xiatian Zhu, Yi-Zhe Song, and Tao Xiang. 2024. PartCraft: Crafting Creative Objects by Parts. In Proceedings of the European Conference on Computer Vision. Springer, 420\u2013437."},{"key":"e_1_3_3_2_35_1","unstructured":"OpenAI. 2025. GPT-image-1 System Card. https:\/\/openai.com\/index\/image-generation-api\/."},{"key":"e_1_3_3_2_36_1","first-page":"8748","volume-title":"International Conference on Machine Learning(ICML)","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong\u00a0Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et\u00a0al. 2021. Learning transferable visual models from natural language supervision. In International Conference on Machine Learning(ICML). 8748\u20138763."},{"key":"e_1_3_3_2_37_1","unstructured":"Colin Raffel Noam Shazeer Adam Roberts Katherine Lee Sharan Narang Michael Matena Yanqi Zhou Wei Li and Peter\u00a0J Liu. 2020. Exploring the limits of transfer learning with a unified text-to-text transformer. Journal of machine learning research 21 140 (2020) 1\u201367."},{"key":"e_1_3_3_2_38_1","first-page":"8821","volume-title":"Proceedings of the International conference on machine learning","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 International conference on machine learning. 8821\u20138831."},{"key":"e_1_3_3_2_39_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-demo.25"},{"key":"e_1_3_3_2_40_1","doi-asserted-by":"crossref","unstructured":"Elad Richardson Kfir Goldberg Yuval Alaluf and Daniel Cohen-Or. 2024. ConceptLab: Creative Concept Generation using VLM-Guided Diffusion Prior Constraints. ACM Transactions on Graphics 43 3 (2024) 1\u201314.","DOI":"10.1145\/3659578"},{"key":"e_1_3_3_2_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_3_2_42_1","first-page":"36479","volume-title":"Proceedings of the Advances in Neural Information Processing Systems (NeurIPS)","author":"Saharia Chitwan","year":"2022","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. In Proceedings of the Advances in Neural Information Processing Systems (NeurIPS). 36479\u201336494."},{"key":"e_1_3_3_2_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00852"},{"key":"e_1_3_3_2_44_1","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR)","author":"Song Jiaming","year":"2021","unstructured":"Jiaming Song, Chenlin Meng, and Stefano Ermon. 2021. Denoising Diffusion Implicit Models. In Proceedings of the International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_3_2_45_1","unstructured":"Viacheslav Surkov Chris Wendler Mikhail Terekhov Justin Deschenaux Robert West and Caglar Gulcehre. 2024. Unpacking sdxl turbo: Interpreting text-to-image models with sparse autoencoders. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2410.22366 (2024)."},{"key":"e_1_3_3_2_46_1","doi-asserted-by":"crossref","unstructured":"Gemma\u00a0Canet Tarr\u00e9s Zhe Lin Zhifei Zhang He Zhang Andrew Gilbert John Collomosse and Soo\u00a0Ye Kim. 2025. Multitwine: Multi-Object Compositing with Text and Layout Control. arXiv:https:\/\/arXiv.org\/abs\/2502.05165 (2025).","DOI":"10.1109\/CVPR52734.2025.00758"},{"key":"e_1_3_3_2_47_1","unstructured":"Jiangshan Wang Junfu Pu Zhongang Qi Jiayi Guo Yue Ma Nisha Huang Yuxin Chen Xiu Li and Ying Shan. 2024. Taming rectified flow for inversion and editing. arXiv:https:\/\/arXiv.org\/abs\/2411.04746 (2024)."},{"key":"e_1_3_3_2_48_1","unstructured":"Xin Xie and Dong Gong. 2024. DyMO: Training-Free Diffusion Model Alignment with Dynamic Multi-Objective Scheduling. arXiv:https:\/\/arXiv.org\/abs\/2412.00759 (2024)."},{"key":"e_1_3_3_2_49_1","doi-asserted-by":"crossref","unstructured":"Zeren Xiong Zikun Chen Zedong Zhang Xiang Li Ying Tai Jian Yang and Jun Li. 2025. Category-Aware 3D Object Composition with Disentangled Texture and Shape Multi-view Diffusion. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2509.02357 (2025).","DOI":"10.1145\/3746027.3755154"},{"key":"e_1_3_3_2_50_1","volume-title":"Proceedings of the Annual Conference on Neural Information Processing Systems (NeurIPS)","author":"Xiong Zeren","year":"2024","unstructured":"Zeren Xiong, Zedong Zhang, Zikun Chen, Shuo Chen, Xiang Li, Gan Sun, Jian Yang, and Jun Li. 2024. Novel Object Synthesis via Adaptive Text-Image Harmony. In Proceedings of the Annual Conference on Neural Information Processing Systems (NeurIPS)."},{"key":"e_1_3_3_2_51_1","first-page":"9452","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Xu Sihan","year":"2024","unstructured":"Sihan Xu, Yidong Huang, Jiayi Pan, Ziqiao Ma, and Joyce Chai. 2024. Inversion-Free Image Editing with Natural Language. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 9452\u20139461."}],"event":{"name":"SA Conference Papers '25: SIGGRAPH Asia 2025 Conference Papers","location":"Hong Kong Hong Kong","acronym":"SA Conference Papers '25","sponsor":["SIGGRAPH ACM Special Interest Group on Computer Graphics and Interactive Techniques"]},"container-title":["Proceedings of the SIGGRAPH Asia 2025 Conference Papers"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3757377.3763944","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T03:26:31Z","timestamp":1765250791000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3757377.3763944"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,14]]},"references-count":50,"alternative-id":["10.1145\/3757377.3763944","10.1145\/3757377"],"URL":"https:\/\/doi.org\/10.1145\/3757377.3763944","relation":{},"subject":[],"published":{"date-parts":[[2025,12,14]]},"assertion":[{"value":"2025-12-14","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}