{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,7]],"date-time":"2026-11-07T07:21:24Z","timestamp":1794036084917,"version":"4.8.0"},"publisher-location":"New York, NY, USA","reference-count":41,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3755395","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T06:54:15Z","timestamp":1761375255000},"page":"8244-8252","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["SmartFreeEdit: Mask-Free Spatial-Aware Image Editing with Complex Instruction Understanding"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-4619-6780","authenticated-orcid":false,"given":"Qianqian","family":"Sun","sequence":"first","affiliation":[{"name":"Institute of Artificial Intelligence (TeleAI), China Telecom, Shanghai, China and University of Hong Kong, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-4698-7835","authenticated-orcid":false,"given":"Jixiang","family":"Luo","sequence":"additional","affiliation":[{"name":"Institute of Artificial Intelligence (TeleAI), China Telecom, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8774-3725","authenticated-orcid":false,"given":"Dell","family":"Zhang","sequence":"additional","affiliation":[{"name":"Institute of Artificial Intelligence (TeleAI), China Telecom, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0019-4197","authenticated-orcid":false,"given":"Xuelong","family":"Li","sequence":"additional","affiliation":[{"name":"Institute of Artificial Intelligence (TeleAI), China Telecom, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Blended latent diffusion. ACM transactions on graphics (TOG) 42, 4","author":"Avrahami Omri","year":"2023","unstructured":"Omri Avrahami, Ohad Fried, and Dani Lischinski. 2023. Blended latent diffusion. ACM transactions on graphics (TOG) 42, 4 (2023), 1--11."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"crossref","unstructured":"Tim Brooks Aleksander Holynski and Alexei A Efros. 2023. Instructpix2pix: Learning to follow image editing instructions. 18392--18402 pages.","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"e_1_3_2_1_3_1","unstructured":"Google DeepMind. 2024. Gemini 2.0: Flash Thinking. Online. https:\/\/www.deepmind.com\/gemini\/flash-thinking\/"},{"key":"e_1_3_2_1_4_1","first-page":"16222","article-title":"Diffusion self-guidance for controllable image generation","volume":"36","author":"Epstein Dave","year":"2023","unstructured":"Dave Epstein, Allan Jabri, Ben Poole, Alexei Efros, and Aleksander Holynski. 2023. Diffusion self-guidance for controllable image generation. Advances in Neural Information Processing Systems 36 (2023), 16222--16239.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_5_1","unstructured":"Tsu-Jui Fu Wenze Hu Xianzhi Du William YangWang Yinfei Yang and Zhe Gan. 2023. Guiding instruction-based image editing via multimodal large language models."},{"key":"e_1_3_2_1_6_1","volume-title":"Instructdiffusion: A generalist modeling interface for vision tasks. 12709--12720 pages.","author":"Geng Zigang","year":"2024","unstructured":"Zigang Geng, Binxin Yang, Tiankai Hang, Chen Li, Shuyang Gu, Ting Zhang, Jianmin Bao, Zheng Zhang, Houqiang Li, Han Hu, et al. 2024. Instructdiffusion: A generalist modeling interface for vision tasks. 12709--12720 pages."},{"key":"e_1_3_2_1_7_1","unstructured":"Yi Huang Jiancheng Huang Yifan Liu Mingfu Yan Jiaxi Lv Jianzhuang Liu Wei Xiong He Zhang Liangliang Cao and Shifeng Chen. 2024. Diffusion model-based image editing: A survey."},{"key":"e_1_3_2_1_8_1","volume-title":"Smartedit: Exploring complex instruction-based image editing with multimodal large language models. 8362--8371 pages.","author":"Huang Yuzhou","year":"2024","unstructured":"Yuzhou Huang, Liangbin Xie, Xintao Wang, Ziyang Yuan, Xiaodong Cun, Yixiao Ge, Jiantao Zhou, Chao Dong, Rui Huang, Ruimao Zhang, et al. 2024. Smartedit: Exploring complex instruction-based image editing with multimodal large language models. 8362--8371 pages."},{"key":"e_1_3_2_1_9_1","volume-title":"Brushnet: A plug-and-play image inpainting model with decomposed dual-branch diffusion. 150--168 pages.","author":"Ju Xuan","year":"2024","unstructured":"Xuan Ju, Xian Liu, Xintao Wang, Yuxuan Bian, Ying Shan, and Qiang Xu. 2024. Brushnet: A plug-and-play image inpainting model with decomposed dual-branch diffusion. 150--168 pages."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"crossref","unstructured":"Alexander Kirillov Eric Mintun Nikhila Ravi Hanzi Mao Chloe Rolland Laura Gustafson Tete Xiao Spencer Whitehead Alexander C Berg Wan-Yen Lo et al. 2023. Segment anything. 4015--4026 pages.","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"e_1_3_2_1_11_1","volume-title":"Lisa: Reasoning segmentation via large language model. 9579--9589 pages.","author":"Lai Xin","year":"2024","unstructured":"Xin Lai, Zhuotao Tian, Yukang Chen, Yanwei Li, Yuhui Yuan, Shu Liu, and Jiaya Jia. 2024. Lisa: Reasoning segmentation via large language model. 9579--9589 pages."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00598"},{"key":"e_1_3_2_1_13_1","volume-title":"Brushedit: All-in-one image inpainting and editing.","author":"Li Yaowei","year":"2024","unstructured":"Yaowei Li, Yuxuan Bian, Xuan Ju, Zhaoyang Zhang, Ying Shan, Yuexian Zou, and Qiang Xu. 2024. Brushedit: All-in-one image inpainting and editing."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"crossref","unstructured":"Shilong Liu Zhaoyang Zeng Tianhe Ren Feng Li Hao Zhang Jie Yang Qing Jiang Chunyuan Li Jianwei Yang Hang Su et al. 2024. Grounding dino: Marrying dino with grounded pre-training for open-set object detection. 38--55 pages.","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"e_1_3_2_1_15_1","volume-title":"Wen Wang, Zhiheng Liu, Qifeng Chen, and Yujun Shen.","author":"Liu Zichen","year":"2024","unstructured":"Zichen Liu, Yue Yu, Hao Ouyang, Qiuyu Wang, Ka Leong Cheng, Wen Wang, Zhiheng Liu, Qifeng Chen, and Yujun Shen. 2024. Magicquill: An intelligent interactive image editing system."},{"key":"e_1_3_2_1_16_1","volume-title":"Hd-painter: High-resolution and promptfaithful text-guided image inpainting with diffusion models.","author":"Manukyan Hayk","year":"2023","unstructured":"Hayk Manukyan, Andranik Sargsyan, Barsegh Atanyan, ZhangyangWang, Shant Navasardyan, and Humphrey Shi. 2023. Hd-painter: High-resolution and promptfaithful text-guided image inpainting with diffusion models."},{"key":"e_1_3_2_1_17_1","unstructured":"Naoki Matsunaga Masato Ishii Akio Hayakawa Kenji Suzuki and Takuya Narihira. 2022. Fine-grained image editing by pixel-wise guidance using diffusion models."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"crossref","unstructured":"Chong Mou Xintao Wang Liangbin Xie Yanze Wu Jian Zhang Zhongang Qi and Ying Shan. 2024. T2i-adapter: Learning adapters to dig out more controllable ability for text-to-image diffusion models. 4296--4304 pages.","DOI":"10.1609\/aaai.v38i5.28226"},{"key":"e_1_3_2_1_19_1","volume-title":"Flexedit: Flexible and controllable diffusion-based object-centric image editing.","author":"Nguyen Trong-Tung","year":"2024","unstructured":"Trong-Tung Nguyen, Duc-Anh Nguyen, Anh Tran, and Cuong Pham. 2024. Flexedit: Flexible and controllable diffusion-based object-centric image editing."},{"key":"e_1_3_2_1_20_1","unstructured":"OpenAI. 2024. GPT-4o System Card. Online. https:\/\/openai.com\/index\/gpt-4osystem-card\/"},{"key":"e_1_3_2_1_21_1","unstructured":"Zhiliang Peng Wenhui Wang Li Dong Yaru Hao Shaohan Huang Shuming Ma and Furu Wei. 2023. Kosmos-2: Grounding multimodal large language models to the world."},{"key":"e_1_3_2_1_22_1","volume-title":"Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al.","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. 8748--8763 pages."},{"key":"e_1_3_2_1_23_1","volume-title":"Glamm: Pixel grounding large multimodal model. 13009--13018 pages.","author":"Rasheed Hanoona","year":"2024","unstructured":"Hanoona Rasheed, Muhammad Maaz, Sahal Shaji, Abdelrahman Shaker, Salman Khan, Hisham Cholakkal, Rao M Anwer, Eric Xing, Ming-Hsuan Yang, and Fahad S Khan. 2024. Glamm: Pixel grounding large multimodal model. 13009--13018 pages."},{"key":"e_1_3_2_1_24_1","unstructured":"Tianhe Ren Shilong Liu Ailing Zeng Jing Lin Kunchang Li He Cao Jiayu Chen Xinyu Huang Yukang Chen Feng Yan et al. 2024. Grounded sam: Assembling open-world models for diverse visual tasks."},{"key":"e_1_3_2_1_25_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. 10684--10695 pages.","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_2_1_26_1","unstructured":"Runway. 2022. Stable Diffusion v1--5. Online. https:\/\/huggingface.co\/stablediffusion-v1--5\/stable-diffusion-v1--5"},{"key":"e_1_3_2_1_27_1","unstructured":"Runway. 2024. GPT-4o System Card. Online. https:\/\/huggingface.co\/stabilityai\/stable-diffusion-xl-base-1.0"},{"key":"e_1_3_2_1_28_1","volume-title":"Mi-gan: A simple baseline for image inpainting on mobile devices. 7335--7345 pages.","author":"Sargsyan Andranik","year":"2023","unstructured":"Andranik Sargsyan, Shant Navasardyan, Xingqian Xu, and Humphrey Shi. 2023. Mi-gan: A simple baseline for image inpainting on mobile devices. 7335--7345 pages."},{"key":"e_1_3_2_1_29_1","unstructured":"Peize Sun Yi Jiang Shoufa Chen Shilong Zhang Bingyue Peng Ping Luo and Zehuan Yuan. 2024. Autoregressive model beats diffusion: Llama for scalable image generation."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"crossref","unstructured":"Roman Suvorov Elizaveta Logacheva Anton Mashikhin Anastasia Remizova Arsenii Ashukha Aleksei Silvestrov Naejin Kong Harshith Goka Kiwoong Park and Victor Lempitsky. 2022. Resolution-robust large mask inpainting with fourier convolutions. 2149--2159 pages.","DOI":"10.1109\/WACV51458.2022.00323"},{"key":"e_1_3_2_1_31_1","volume-title":"Visual autoregressive modeling: Scalable image generation via next-scale prediction. Advances in neural information processing systems 37","author":"Tian Keyu","year":"2024","unstructured":"Keyu Tian, Yi Jiang, Zehuan Yuan, Bingyue Peng, and Liwei Wang. 2024. Visual autoregressive modeling: Scalable image generation via next-scale prediction. Advances in neural information processing systems 37 (2024), 84839--84865."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"crossref","unstructured":"Ziyu Wan Jingbo Zhang Dongdong Chen and Jing Liao. 2021. High-fidelity pluralistic image completion with transformers. 4692--4701 pages.","DOI":"10.1109\/ICCV48922.2021.00465"},{"key":"e_1_3_2_1_33_1","first-page":"61501","article-title":"Visionllm: Large language model is also an open-ended decoder for vision-centric tasks","volume":"36","author":"Wang Wenhai","year":"2023","unstructured":"Wenhai Wang, Zhe Chen, Xiaokang Chen, Jiannan Wu, Xizhou Zhu, Gang Zeng, Ping Luo, Tong Lu, Jie Zhou, Yu Qiao, et al. 2023. Visionllm: Large language model is also an open-ended decoder for vision-centric tasks. Advances in Neural Information Processing Systems 36 (2023), 61501--61513.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_34_1","first-page":"128374","article-title":"Genartist: Multimodal llm as an agent for unified image generation and editing","volume":"37","author":"Wang Zhenyu","year":"2024","unstructured":"Zhenyu Wang, Aoxue Li, Zhenguo Li, and Xihui Liu. 2024. Genartist: Multimodal llm as an agent for unified image generation and editing. Advances in Neural Information Processing Systems 37 (2024), 128374--128395.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_35_1","volume-title":"Smartbrush: Text and shape guided object inpainting with diffusion model. 22428--22437 pages.","author":"Xie Shaoan","year":"2023","unstructured":"Shaoan Xie, Zhifei Zhang, Zhe Lin, Tobias Hinz, and Kun Zhang. 2023. Smartbrush: Text and shape guided object inpainting with diffusion model. 22428--22437 pages."},{"key":"e_1_3_2_1_36_1","unstructured":"Xingqian Xu Shant Navasardyan Vahram Tadevosyan Andranik Sargsyan Yadong Mu and Humphrey Shi. 2023. Image completion with heterogeneously filtered spectral hints. 4591--4601 pages."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"crossref","unstructured":"Binxin Yang Shuyang Gu Bo Zhang Ting Zhang Xuejin Chen Xiaoyan Sun Dong Chen and Fang Wen. 2023. Paint by example: Exemplar-based image editing with diffusion models. 18381--18391 pages.","DOI":"10.1109\/CVPR52729.2023.01763"},{"key":"e_1_3_2_1_38_1","first-page":"31428","article-title":"Magicbrush: A manually annotated dataset for instruction-guided image editing","volume":"36","author":"Zhang Kai","year":"2023","unstructured":"Kai Zhang, Lingbo Mo, Wenhu Chen, Huan Sun, and Yu Su. 2023. Magicbrush: A manually annotated dataset for instruction-guided image editing. Advances in Neural Information Processing Systems 36 (2023), 31428--31449.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"crossref","unstructured":"Lvmin Zhang Anyi Rao and Maneesh Agrawala. 2023. Adding conditional control to text-to-image diffusion models. 3836--3847 pages.","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"crossref","unstructured":"Shilong Zhang Peize Sun Shoufa Chen Min Xiao Wenqi Shao Wenwei Zhang Yu Liu Kai Chen and Ping Luo. 2025. GPT4RoI: Instruction Tuning Large Language Model on Region-of-Interest. arXiv:2307.03601 [cs.CV] https:\/\/arxiv.org\/abs\/2307.03601","DOI":"10.1007\/978-3-031-91813-1_4"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"crossref","unstructured":"Jun Zhou Jiahao Li Zunnan Xu Hanhui Li Yiji Cheng Fa-Ting Hong Qin Lin Qinglin Lu and Xiaodan Liang. 2025. FireEdit: Fine-grained Instruction-based Image Editing via Region-aware Vision Language Model.","DOI":"10.1109\/CVPR52734.2025.01222"}],"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\/3746027.3755395","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T03:59:18Z","timestamp":1765339158000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3755395"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":41,"alternative-id":["10.1145\/3746027.3755395","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3755395","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"}}]}}