{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T14:56:02Z","timestamp":1781535362063,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":39,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T00:00:00Z","timestamp":1781481600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,6,16]]},"DOI":"10.1145\/3805622.3810678","type":"proceedings-article","created":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T14:42:57Z","timestamp":1781534577000},"page":"2732-2740","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["SlimNet: High-Quality and Efficient Object Removal by Eliciting Latent Capabilities of Diffusion Models"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-7873-2289","authenticated-orcid":false,"given":"Xiao","family":"Ma","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China and Lenovo Ltd, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9954-0693","authenticated-orcid":false,"given":"Jin","family":"Yuan","sequence":"additional","affiliation":[{"name":"Lenovo Ltd, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8759-4811","authenticated-orcid":false,"given":"Yao","family":"Zhang","sequence":"additional","affiliation":[{"name":"Lenovo Ltd, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6886-7319","authenticated-orcid":false,"given":"Cheng","family":"Zhong","sequence":"additional","affiliation":[{"name":"Lenovo Ltd, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5216-3827","authenticated-orcid":false,"given":"Zhongchao","family":"Shi","sequence":"additional","affiliation":[{"name":"Lenovo Ltd, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2290-1785","authenticated-orcid":false,"given":"Jianping","family":"Fan","sequence":"additional","affiliation":[{"name":"Lenovo Ltd, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6623-2945","authenticated-orcid":false,"given":"Guihua","family":"Zeng","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,6,15]]},"reference":[{"key":"e_1_3_3_1_2_2","doi-asserted-by":"crossref","unstructured":"Alibaba Group (Alimama Creative). 2024. SD3-Controlnet-Inpainting: A Finetuned ControlNet Inpainting Model Based on SD3-Medium. https:\/\/huggingface.co\/alimama-creative\/SD3-Controlnet-Inpainting. Accessed: 2024-10-12.","DOI":"10.1109\/ACCESS.2024.3520002"},{"key":"e_1_3_3_1_3_2","doi-asserted-by":"crossref","unstructured":"Connelly Barnes Eli Shechtman Adam Finkelstein and Dan\u00a0B Goldman. 2009. PatchMatch: A randomized correspondence algorithm for structural image editing. ACM Trans. Graph. 28 3 (2009) 24.","DOI":"10.1145\/1531326.1531330"},{"key":"e_1_3_3_1_4_2","doi-asserted-by":"publisher","DOI":"10.1145\/344779.344972"},{"key":"e_1_3_3_1_5_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00788"},{"key":"e_1_3_3_1_6_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00630"},{"key":"e_1_3_3_1_7_2","doi-asserted-by":"crossref","unstructured":"Antonio Criminisi Patrick P\u00e9rez and Kentaro Toyama. 2004. Region filling and object removal by exemplar-based image inpainting. IEEE Transactions on image processing 13 9 (2004) 1200\u20131212.","DOI":"10.1109\/TIP.2004.833105"},{"key":"e_1_3_3_1_8_2","doi-asserted-by":"crossref","unstructured":"Yi\u011fit Ekin Ahmet\u00a0Burak Yildirim Erdem\u00a0Eren \u00c7a\u011flar Aykut Erdem Erkut Erdem and Aysegul Dundar. 2024. Clipaway: Harmonizing focused embeddings for removing objects via diffusion models. Advances in Neural Information Processing Systems 37 (2024) 17572\u201317601.","DOI":"10.52202\/079017-0559"},{"key":"e_1_3_3_1_9_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.265"},{"key":"e_1_3_3_1_10_2","doi-asserted-by":"crossref","unstructured":"Ian Goodfellow Jean Pouget-Abadie Mehdi Mirza Bing Xu David Warde-Farley Sherjil Ozair Aaron Courville and Yoshua Bengio. 2020. Generative adversarial networks. Commun. ACM 63 11 (2020) 139\u2013144.","DOI":"10.1145\/3422622"},{"key":"e_1_3_3_1_11_2","doi-asserted-by":"crossref","unstructured":"James Hays and Alexei\u00a0A Efros. 2007. Scene completion using millions of photographs. ACM Transactions on graphics (TOG) 26 3 (2007) 4\u2013es.","DOI":"10.1145\/1276377.1276382"},{"key":"e_1_3_3_1_12_2","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 30 (2017)."},{"key":"e_1_3_3_1_13_2","unstructured":"Jonathan Ho Ajay Jain and Pieter Abbeel. 2020. Denoising diffusion probabilistic models. Advances in neural information processing systems 33 (2020) 6840\u20136851."},{"key":"e_1_3_3_1_14_2","doi-asserted-by":"crossref","unstructured":"Satoshi Iizuka Edgar Simo-Serra and Hiroshi Ishikawa. 2017. Globally and locally consistent image completion. ACM Transactions on Graphics (ToG) 36 4 (2017) 1\u201314.","DOI":"10.1145\/3072959.3073659"},{"key":"e_1_3_3_1_15_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_43"},{"key":"e_1_3_3_1_16_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2003.1238360"},{"key":"e_1_3_3_1_17_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01309"},{"key":"e_1_3_3_1_18_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_6"},{"key":"e_1_3_3_1_19_2","first-page":"725","volume-title":"European conference on computer vision","author":"Liu Hongyu","year":"2020","unstructured":"Hongyu Liu, Bin Jiang, Yibing Song, Wei Huang, and Chao Yang. 2020. Rethinking image inpainting via a mutual encoder-decoder with feature equalizations. In European conference on computer vision. Springer, 725\u2013741."},{"key":"e_1_3_3_1_20_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01117"},{"key":"e_1_3_3_1_21_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_47"},{"key":"e_1_3_3_1_22_2","unstructured":"Chenlin Meng Yutong He Yang Song Jiaming Song Jiajun Wu Jun-Yan Zhu and Stefano Ermon. 2021. Sdedit: Guided image synthesis and editing with stochastic differential equations. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2108.01073 (2021)."},{"key":"e_1_3_3_1_23_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.278"},{"key":"e_1_3_3_1_24_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00027"},{"key":"e_1_3_3_1_25_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_3_1_26_2","first-page":"542","volume-title":"Proceedings of the British Machine Vision Conference (BMVC)","author":"Sagong Min-Cheol","year":"2022","unstructured":"Min-Cheol Sagong, Yoon-Jae Yeo, Seung-Won Jung, and Sung-Jea Ko. 2022. RORD: A Real-world Object Removal Dataset.. In Proceedings of the British Machine Vision Conference (BMVC). 542."},{"key":"e_1_3_3_1_27_2","doi-asserted-by":"crossref","unstructured":"Christoph Schuhmann Romain Beaumont Richard Vencu Cade Gordon Ross Wightman Mehdi Cherti Theo Coombes Aarush Katta Clayton Mullis Mitchell Wortsman et\u00a0al. 2022. Laion-5b: An open large-scale dataset for training next generation image-text models. Advances in neural information processing systems 35 (2022) 25278\u201325294.","DOI":"10.52202\/068431-1833"},{"key":"e_1_3_3_1_28_2","unstructured":"Stability AI. 2024. Stable Diffusion 3 Medium. https:\/\/huggingface.co\/stabilityai\/stable-diffusion-3-medium. Accessed: 2024."},{"key":"e_1_3_3_1_29_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i19.34285"},{"key":"e_1_3_3_1_30_2","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00323"},{"key":"e_1_3_3_1_31_2","doi-asserted-by":"crossref","unstructured":"Alexandru Telea. 2004. An image inpainting technique based on the fast marching method. Journal of graphics tools 9 1 (2004) 23\u201334.","DOI":"10.1080\/10867651.2004.10487596"},{"key":"e_1_3_3_1_32_2","unstructured":"Ultralytics. 2023. Ultralytics YOLO. https:\/\/github.com\/ultralytics\/ultralytics. Code repository."},{"key":"e_1_3_3_1_33_2","doi-asserted-by":"crossref","unstructured":"Zhou Wang Alan\u00a0C Bovik Hamid\u00a0R Sheikh and Eero\u00a0P Simoncelli. 2004. Image quality assessment: from error visibility to structural similarity. IEEE transactions on image processing 13 4 (2004) 600\u2013612.","DOI":"10.1109\/TIP.2003.819861"},{"key":"e_1_3_3_1_34_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00577"},{"key":"e_1_3_3_1_35_2","unstructured":"Yongsheng Yu Ziyun Zeng Haitian Zheng and Jiebo Luo. 2025. Omnipaint: Mastering object-oriented editing via disentangled insertion-removal inpainting. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2503.08677 (2025)."},{"key":"e_1_3_3_1_36_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00158"},{"key":"e_1_3_3_1_37_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"e_1_3_3_1_38_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"e_1_3_3_1_39_2","unstructured":"Jixin Zhao Shangchen Zhou Zhouxia Wang Peiqing Yang and Chen\u00a0Change Loy. 2025. ObjectClear: Complete Object Removal via Object-Effect Attention. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2505.22636 (2025)."},{"key":"e_1_3_3_1_40_2","first-page":"195","volume-title":"European Conference on Computer Vision","author":"Zhuang Junhao","year":"2024","unstructured":"Junhao Zhuang, Yanhong Zeng, Wenran Liu, Chun Yuan, and Kai Chen. 2024. A task is worth one word: Learning with task prompts for high-quality versatile image inpainting. In European Conference on Computer Vision. Springer, 195\u2013211."}],"event":{"name":"ICMR '26: International Conference on Multimedia Retrieval","location":"Amsterdam The Netherlands","acronym":"ICMR '26","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 2026 International Conference on Multimedia Retrieval"],"original-title":[],"deposited":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T14:46:05Z","timestamp":1781534765000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3805622.3810678"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,15]]},"references-count":39,"alternative-id":["10.1145\/3805622.3810678","10.1145\/3805622"],"URL":"https:\/\/doi.org\/10.1145\/3805622.3810678","relation":{},"subject":[],"published":{"date-parts":[[2026,6,15]]},"assertion":[{"value":"2026-06-15","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}