{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T15:45:49Z","timestamp":1780674349025,"version":"3.54.1"},"publisher-location":"Cham","reference-count":52,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031733895","type":"print"},{"value":"9783031733901","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T00:00:00Z","timestamp":1730332800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T00:00:00Z","timestamp":1730332800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-3-031-73390-1_13","type":"book-chapter","created":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T16:24:01Z","timestamp":1730305441000},"page":"215-231","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["MagicEraser: Erasing Any Objects via\u00a0Semantics-Aware Control"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3595-8361","authenticated-orcid":false,"given":"Fan","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zixiao","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8443-6877","authenticated-orcid":false,"given":"Yi","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7960-9382","authenticated-orcid":false,"given":"Jianzhuang","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Renjing","family":"Pei","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bin","family":"Shao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Songcen","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,10,31]]},"reference":[{"key":"13_CR1","doi-asserted-by":"crossref","unstructured":"Brooks, T., Holynski, A., Efros, A.A.: Instructpix2pix: learning to follow image editing instructions. In: CVPR, pp. 18392\u201318402 (2023)","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"13_CR2","doi-asserted-by":"crossref","unstructured":"Cao, H., et al.: A survey on generative diffusion models. IEEE TKDE (2024)","DOI":"10.1109\/TKDE.2024.3361474"},{"key":"13_CR3","doi-asserted-by":"crossref","unstructured":"Cheng, B., Misra, I., Schwing, A.G., Kirillov, A., Girdhar, R.: Masked-attention mask transformer for universal image segmentation. In: CVPR, pp. 1290\u20131299 (2022)","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"13_CR4","doi-asserted-by":"crossref","unstructured":"Croitoru, F.A., Hondru, V., Ionescu, R.T., Shah, M.: Diffusion models in vision: A survey. IEEE TPAMI (2023)","DOI":"10.1109\/TPAMI.2023.3261988"},{"key":"13_CR5","unstructured":"Epstein, D., Jabri, A., Poole, B., Efros, A.A., Holynski, A.: Diffusion self-guidance for controllable image generation. arXiv preprint arXiv:2306.00986 (2023)"},{"key":"13_CR6","unstructured":"Gal, R., et al.: An image is worth one word: Personalizing text-to-image generation using textual inversion. arXiv preprint arXiv:2208.01618 (2022)"},{"key":"13_CR7","unstructured":"Goodfellow, I.J., et al.: Generative adversarial networks. arXiv preprint arXiv:1406.2661 (2014)"},{"key":"13_CR8","unstructured":"Hertz, A., Mokady, R., Tenenbaum, J., Aberman, K., Pritch, Y., Cohen-or, D.: Prompt-to-prompt image editing with cross-attention control. In: ICLR (2023)"},{"key":"13_CR9","unstructured":"Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B., Hochreiter, S.: Gans trained by a two time-scale update rule converge to a local nash equilibrium. In: NeurIPS. vol.\u00a030 (2017)"},{"key":"13_CR10","unstructured":"Ho, J., et\u00a0al.: Imagen video: High definition video generation with diffusion models. arXiv preprint arXiv:2210.02303 (2022)"},{"key":"13_CR11","first-page":"6840","volume":"33","author":"J Ho","year":"2020","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. NeurIPS 33, 6840\u20136851 (2020)","journal-title":"NeurIPS"},{"issue":"1","key":"13_CR12","first-page":"2249","volume":"23","author":"J Ho","year":"2022","unstructured":"Ho, J., Saharia, C., Chan, W., Fleet, D.J., Norouzi, M., Salimans, T.: Cascaded diffusion models for high fidelity image generation. JMLR 23(1), 2249\u20132281 (2022)","journal-title":"JMLR"},{"key":"13_CR13","unstructured":"Hu, E.J., et al.: Lora: Low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685 (2021)"},{"key":"13_CR14","doi-asserted-by":"crossref","unstructured":"Huang, Y., Huang, J., Liu, J., Dong, Y., Lv, J., Chen, S.: Wavedm: wavelet-based diffusion models for image restoration. IEEE TMM (2024)","DOI":"10.1109\/TMM.2024.3359769"},{"key":"13_CR15","unstructured":"Huang, Y., et al.: Diffusion model-based image editing: A survey. arXiv preprint arXiv:2402.17525 (2024)"},{"key":"13_CR16","doi-asserted-by":"crossref","unstructured":"Jiang, Y., et al.: Ssh: A self-supervised framework for image harmonization. In: ICCV, pp. 4832\u20134841 (2021)","DOI":"10.1109\/ICCV48922.2021.00479"},{"key":"13_CR17","doi-asserted-by":"crossref","unstructured":"Karras, T., Laine, S., Aila, T.: A style-based generator architecture for generative adversarial networks. arXiv preprint arXiv:1812.04948 (2019)","DOI":"10.1109\/CVPR.2019.00453"},{"key":"13_CR18","doi-asserted-by":"crossref","unstructured":"Karras, T., Laine, S., Aittala, M., Hellsten, J., Lehtinen, J., Aila, T.: Analyzing and improving the image quality of stylegan. arXiv preprint arXiv:1912.04958 (2020)","DOI":"10.1109\/CVPR42600.2020.00813"},{"key":"13_CR19","first-page":"23593","volume":"35","author":"B Kawar","year":"2022","unstructured":"Kawar, B., Elad, M., Ermon, S., Song, J.: Denoising diffusion restoration models. NeurIPS 35, 23593\u201323606 (2022)","journal-title":"NeurIPS"},{"key":"13_CR20","doi-asserted-by":"crossref","unstructured":"Kim, Y., Lee, J., Kim, J.H., Ha, J.W., Zhu, J.Y.: Dense text-to-image generation with attention modulation. arXiv preprint arXiv:2308.12964 (2023)","DOI":"10.1109\/ICCV51070.2023.00708"},{"key":"13_CR21","unstructured":"Kingma, D.P., Welling, M.: Auto-encoding variational bayes. In: ICLR (2014)"},{"key":"13_CR22","doi-asserted-by":"crossref","unstructured":"Kuznetsova, A., et al.: The open images dataset v4: Unified image classification, object detection, and visual relationship detection at scale. IJCV (2020)","DOI":"10.1007\/s11263-020-01316-z"},{"key":"13_CR23","doi-asserted-by":"crossref","unstructured":"Li, W., Lin, Z., Zhou, K., Qi, L., Wang, Y., Jia, J.: Mat: Mask-aware transformer for large hole image inpainting. arXiv preprint arXiv:2203.15270 (2022)","DOI":"10.1109\/CVPR52688.2022.01049"},{"key":"13_CR24","unstructured":"Li, W., Yu, X., Zhou, K., Song, Y., Lin, Z.: Image inpainting via iteratively decoupled probabilistic modeling. In: ICLR (2024)"},{"key":"13_CR25","unstructured":"Li, X., et al.: Diffusion models for image restoration and enhancement\u2013a comprehensive survey. arXiv preprint arXiv:2308.09388 (2023)"},{"key":"13_CR26","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T-Y Lin","year":"2014","unstructured":"Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"13_CR27","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning. In: NeurIPS (2023)"},{"key":"13_CR28","doi-asserted-by":"crossref","unstructured":"Liu, W., Cun, X., Pun, C.M., Xia, M., Zhang, Y., Wang, J.: Coordfill: efficient high-resolution image inpainting via parameterized coordinate querying. arXiv preprint arXiv:2303.08524 (2023)","DOI":"10.1609\/aaai.v37i2.25263"},{"key":"13_CR29","doi-asserted-by":"crossref","unstructured":"Lugmayr, A., Danelljan, M., Romero, A., Yu, F., Timofte, R., Van\u00a0Gool, L.: Repaint: Inpainting using denoising diffusion probabilistic models. In: CVPR, pp. 11461\u201311471 (2022)","DOI":"10.1109\/CVPR52688.2022.01117"},{"key":"13_CR30","unstructured":"Meng, C., Song, Y., Song, J., Wu, J., Zhu, J.Y., Ermon, S.: Sdedit: image synthesis and editing with stochastic differential equations. In: ICLR (2022)"},{"key":"13_CR31","unstructured":"Nichol, A.Q., et al.: Glide: towards photorealistic image generation and editing with text-guided diffusion models. In: ICML, pp. 16784\u201316804 (2022)"},{"key":"13_CR32","doi-asserted-by":"crossref","unstructured":"\u00d6zdenizci, O., Legenstein, R.: Restoring vision in adverse weather conditions with patch-based denoising diffusion models. IEEE TPAMI (2023)","DOI":"10.1109\/TPAMI.2023.3238179"},{"key":"13_CR33","unstructured":"Ramesh, A., Dhariwal, P., Nichol, A., Chu, C., Chen, M.: Hierarchical text-conditional image generation with clip latents. arXiv preprint arXiv:2204.06125 (2022)"},{"key":"13_CR34","unstructured":"Ramesh, A., et al.: Zero-shot text-to-image generation. In: ICML, pp. 8821\u20138831 (2021)"},{"key":"13_CR35","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"13_CR36","doi-asserted-by":"crossref","unstructured":"Saharia, C., et al.: Palette: image-to-image diffusion models. In: ACM SIGGRAPH, pp. 1\u201310 (2022)","DOI":"10.1145\/3528233.3530757"},{"key":"13_CR37","doi-asserted-by":"crossref","unstructured":"Saharia, C., et\u00a0al.: Photorealistic text-to-image diffusion models with deep language understanding. In: NeurIPS (2022)","DOI":"10.1145\/3528233.3530757"},{"key":"13_CR38","doi-asserted-by":"crossref","unstructured":"Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., Chen, L.C.: Mobilenetv2: inverted residuals and linear bottlenecks. In: CVPR, pp. 4510\u20134520 (2018)","DOI":"10.1109\/CVPR.2018.00474"},{"key":"13_CR39","unstructured":"Sohl-Dickstein, J., Weiss, E., Maheswaranathan, N., Ganguli, S.: Deep unsupervised learning using nonequilibrium thermodynamics. In: ICML (2015)"},{"key":"13_CR40","unstructured":"Song, J., Meng, C., Ermon, S.: Denoising diffusion implicit models. In: ICLR (2021)"},{"key":"13_CR41","unstructured":"Song, Y., Sohl-Dickstein, J., Kingma, D.P., Kumar, A., Ermon, S., Poole, B.: Score-based generative modeling through stochastic differential equations. In: ICLR (2021)"},{"key":"13_CR42","doi-asserted-by":"crossref","unstructured":"Suvorov, R., et al.: Resolution-robust large mask inpainting with fourier convolutions. In: WACV, pp. 2149\u20132159 (2022)","DOI":"10.1109\/WACV51458.2022.00323"},{"key":"13_CR43","unstructured":"Wang, K., Yang, F., Yang, S., Butt, M.A., van\u00a0de Weijer, J.: Dynamic prompt learning: Addressing cross-attention leakage for text-based image editing. In: NeurIPS (2023)"},{"key":"13_CR44","doi-asserted-by":"crossref","unstructured":"Wang, S., et\u00a0al.: Imagen editor and editbench: Advancing and evaluating text-guided image inpainting. In: CVPR, pp. 18359\u201318369 (2023)","DOI":"10.1109\/CVPR52729.2023.01761"},{"issue":"4","key":"13_CR45","first-page":"600","volume":"13","author":"Z Wang","year":"2004","unstructured":"Wang, Z., Bovik, A.C., Sheikh, H.R., Simoncelli, E.P.: Image quality assessment: from error visibility to structural similarity. IEEE TIP 13(4), 600\u2013612 (2004)","journal-title":"IEEE TIP"},{"key":"13_CR46","doi-asserted-by":"crossref","unstructured":"Xie, S., Zhang, Z., Lin, Z., Hinz, T., Zhang, K.: Smartbrush: text and shape guided object inpainting with diffusion model. In: CVPR, pp. 22428\u201322437 (2023)","DOI":"10.1109\/CVPR52729.2023.02148"},{"key":"13_CR47","unstructured":"Yang, S., Zhang, L., Ma, L., Liu, Y., Fu, J., He, Y.: Magicremover: Tuning-free text-guided image inpainting with diffusion models. arXiv preprint arXiv:2310.02848 (2023)"},{"key":"13_CR48","unstructured":"Yildirim, A.B., Baday, V., Erdem, E., Erdem, A., Dundar, A.: Inst-inpaint: Instructing to remove objects with diffusion models. arXiv preprint arXiv:2304.03246 (2023)"},{"key":"13_CR49","doi-asserted-by":"crossref","unstructured":"Zhang, R., Isola, P., Efros, A.A., Shechtman, E., Wang, O.: The unreasonable effectiveness of deep features as a perceptual metric. arXiv preprint arXiv:1801.03924 (2018)","DOI":"10.1109\/CVPR.2018.00068"},{"key":"13_CR50","unstructured":"Zhao, S., et al.: Large scale image completion via co-modulated generative adversarial networks. arXiv preprint arXiv:2103.10428 (2021)"},{"key":"13_CR51","doi-asserted-by":"crossref","unstructured":"Zhou, B., Lapedriza, A., Khosla, A., Oliva, A., Torralba, A.: Places: a 10 million image database for scene recognition. TPAMI (2017)","DOI":"10.1167\/17.10.296"},{"key":"13_CR52","doi-asserted-by":"crossref","unstructured":"Zhuang, J., Zeng, Y., Liu, W., Yuan, C., Chen, K.: A task is worth one word: Learning with task prompts for high-quality versatile image inpainting. arXiv preprint arXiv:2312.03594 (2023)","DOI":"10.1007\/978-3-031-73636-0_12"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-73390-1_13","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,30]],"date-time":"2024-11-30T14:29:36Z","timestamp":1732976976000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73390-1_13"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,31]]},"ISBN":["9783031733895","9783031733901"],"references-count":52,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73390-1_13","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,31]]},"assertion":[{"value":"31 October 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}