{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T19:30:29Z","timestamp":1750188629743,"version":"3.40.3"},"publisher-location":"Cham","reference-count":48,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031731129"},{"type":"electronic","value":"9783031731136"}],"license":[{"start":{"date-parts":[[2024,11,21]],"date-time":"2024-11-21T00:00:00Z","timestamp":1732147200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,21]],"date-time":"2024-11-21T00:00:00Z","timestamp":1732147200000},"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\/978-3-031-73113-6_23","type":"book-chapter","created":{"date-parts":[[2024,11,20]],"date-time":"2024-11-20T08:49:10Z","timestamp":1732092550000},"page":"396-413","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["DiffuMatting: Synthesizing Arbitrary Objects with\u00a0Matting-Level Annotation"],"prefix":"10.1007","author":[{"given":"Xiaobin","family":"Hu","sequence":"first","affiliation":[]},{"given":"Xu","family":"Peng","sequence":"additional","affiliation":[]},{"given":"Donghao","family":"Luo","sequence":"additional","affiliation":[]},{"given":"Xiaozhong","family":"Ji","sequence":"additional","affiliation":[]},{"given":"Jinlong","family":"Peng","sequence":"additional","affiliation":[]},{"given":"Zhengkai","family":"Jiang","sequence":"additional","affiliation":[]},{"given":"Jiangning","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Taisong","family":"Jin","sequence":"additional","affiliation":[]},{"given":"Chengjie","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Rongrong","family":"Ji","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,11,21]]},"reference":[{"unstructured":"Azadi, S., Tschannen, M., Tzeng, E., Gelly, S., Darrell, T., Lucic, M.: Semantic bottleneck scene generation. arXiv preprint arXiv:1911.11357 (2019)","key":"23_CR1"},{"unstructured":"Azizi, S., Kornblith, S., Saharia, C., Norouzi, M., Fleet, D.J.: Synthetic data from diffusion models improves ImageNet classification. arXiv preprint arXiv:2304.08466 (2023)","key":"23_CR2"},{"unstructured":"Bansal, H., Grover, A.: Leaving reality to imagination: robust classification via generated datasets. arXiv preprint arXiv:2302.02503 (2023)","key":"23_CR3"},{"unstructured":"Baranchuk, D., Rubachev, I., Voynov, A., Khrulkov, V., Babenko, A.: Label-efficient semantic segmentation with diffusion models. In: ICLR (2022)","key":"23_CR4"},{"doi-asserted-by":"crossref","unstructured":"Chen, X., Huang, L., Liu, Y., Shen, Y., Zhao, D., Zhao, H.: AnyDoor: zero-shot object-level image customization. arXiv preprint arXiv:2307.09481 (2023)","key":"23_CR5","DOI":"10.1109\/CVPR52733.2024.00630"},{"unstructured":"Dai, W., et al.: InstructBLIP: towards general-purpose vision-language models with instruction tuning (2023)","key":"23_CR6"},{"unstructured":"Devaranjan, J., Fidler, S., Kar, A.: Unsupervised learning of scene structure for synthetic data generation (9 September 2021), uS Patent App. 17\/117,425 (2021)","key":"23_CR7"},{"issue":"10","key":"23_CR8","doi-asserted-by":"publisher","first-page":"1915","DOI":"10.1109\/TPAMI.2011.272","volume":"34","author":"S Goferman","year":"2011","unstructured":"Goferman, S., Zelnik-Manor, L., Tal, A.: Context-aware saliency detection. IEEE Trans. Pattern Anal. Mach. Intell. 34(10), 1915\u20131926 (2011)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"doi-asserted-by":"crossref","unstructured":"Gu, S., et al.: Vector quantized diffusion model for text-to-image synthesis. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10696\u201310706 (2022)","key":"23_CR9","DOI":"10.1109\/CVPR52688.2022.01043"},{"unstructured":"He, R., et al.: Is synthetic data from generative models ready for image recognition? In: ICLR (2022)","key":"23_CR10"},{"unstructured":"Ho, J., Salimans, T.: Classifier-free diffusion guidance. arXiv preprint arXiv:2207.12598 (2022)","key":"23_CR11"},{"doi-asserted-by":"crossref","unstructured":"Hou, Q., Cheng, M.M., Hu, X., Borji, A., Tu, Z., Torr, P.H.: Deeply supervised salient object detection with short connections. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3203\u20133212 (2017)","key":"23_CR12","DOI":"10.1109\/CVPR.2017.563"},{"doi-asserted-by":"crossref","unstructured":"Kar, A., et al.: Meta-Sim: learning to generate synthetic datasets. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4551\u20134560 (2019)","key":"23_CR13","DOI":"10.1109\/ICCV.2019.00465"},{"key":"23_CR14","first-page":"26565","volume":"35","author":"T Karras","year":"2022","unstructured":"Karras, T., Aittala, M., Aila, T., Laine, S.: Elucidating the design space of diffusion-based generative models. Adv. Neural. Inf. Process. Syst. 35, 26565\u201326577 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"doi-asserted-by":"crossref","unstructured":"Ke, Z., Sun, J., Li, K., Yan, Q., Lau, R.W.: MODNet: real-time trimap-free portrait matting via objective decomposition. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a036, pp. 1140\u20131147 (2022)","key":"23_CR15","DOI":"10.1609\/aaai.v36i1.19999"},{"unstructured":"Kirillov, A., et\u00a0al.: Segment anything. arXiv preprint arXiv:2304.02643 (2023)","key":"23_CR16"},{"doi-asserted-by":"crossref","unstructured":"Le\u00a0Moing, G., Vu, T.H., Jain, H., P\u00e9rez, P., Cord, M.: Semantic palette: guiding scene generation with class proportions. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9342\u20139350 (2021)","key":"23_CR17","DOI":"10.1109\/CVPR46437.2021.00922"},{"doi-asserted-by":"crossref","unstructured":"Li, B., Xue, K., Liu, B., Lai, Y.K.: BBDM: image-to-image translation with Brownian bridge diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1952\u20131961 (2023)","key":"23_CR18","DOI":"10.1109\/CVPR52729.2023.00194"},{"doi-asserted-by":"crossref","unstructured":"Li, D., Ling, H., Kim, S.W., Kreis, K., Fidler, S., Torralba, A.: BigDatasetGAN: synthesizing ImageNet with pixel-wise annotations. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 21330\u201321340 (2022)","key":"23_CR19","DOI":"10.1109\/CVPR52688.2022.02064"},{"doi-asserted-by":"crossref","unstructured":"Li, J., Ma, S., Zhang, J., Tao, D.: Privacy-preserving portrait matting. In: Proceedings of the 29th ACM International Conference on Multimedia, pp. 3501\u20133509 (2021)","key":"23_CR20","DOI":"10.1145\/3474085.3475512"},{"issue":"2","key":"23_CR21","doi-asserted-by":"publisher","first-page":"246","DOI":"10.1007\/s11263-021-01541-0","volume":"130","author":"J Li","year":"2022","unstructured":"Li, J., Zhang, J., Maybank, S.J., Tao, D.: Bridging composite and real: towards end-to-end deep image matting. Int. J. Comput. Vision 130(2), 246\u2013266 (2022)","journal-title":"Int. J. Comput. Vision"},{"doi-asserted-by":"crossref","unstructured":"Li, J., Zhang, J., Tao, D.: Deep automatic natural image matting. arXiv preprint arXiv:2107.07235 (2021)","key":"23_CR22","DOI":"10.24963\/ijcai.2021\/111"},{"doi-asserted-by":"crossref","unstructured":"Liew, J.H., Cohen, S., Price, B., Mai, L., Feng, J.: Deep interactive thin object selection. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 305\u2013314 (2021)","key":"23_CR23","DOI":"10.1109\/WACV48630.2021.00035"},{"doi-asserted-by":"crossref","unstructured":"Lin, S., Ryabtsev, A., Sengupta, S., Curless, B.L., Seitz, S.M., Kemelmacher-Shlizerman, I.: Real-time high-resolution background matting. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8762\u20138771 (2021)","key":"23_CR24","DOI":"10.1109\/CVPR46437.2021.00865"},{"doi-asserted-by":"crossref","unstructured":"Liu, F., Tran, L., Liu, X.: Fully understanding generic objects: modeling, segmentation, and reconstruction. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7423\u20137433 (2021)","key":"23_CR25","DOI":"10.1109\/CVPR46437.2021.00734"},{"doi-asserted-by":"crossref","unstructured":"Lu, H., Dai, Y., Shen, C., Xu, S.: Indices matter: learning to index for deep image matting. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3266\u20133275 (2019)","key":"23_CR26","DOI":"10.1109\/ICCV.2019.00336"},{"doi-asserted-by":"crossref","unstructured":"Park, M., Yun, J., Choi, S., Choo, J.: Learning to generate semantic layouts for higher text-image correspondence in text-to-image synthesis. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 7591\u20137600 (2023)","key":"23_CR27","DOI":"10.1109\/ICCV51070.2023.00698"},{"doi-asserted-by":"crossref","unstructured":"Peebles, W., Xie, S.: Scalable diffusion models with transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4195\u20134205 (2023)","key":"23_CR28","DOI":"10.1109\/ICCV51070.2023.00387"},{"unstructured":"Podell, D., et al.: SDXL: improving latent diffusion models for high-resolution image synthesis. arXiv preprint arXiv:2307.01952 (2023)","key":"23_CR29"},{"doi-asserted-by":"crossref","unstructured":"Qiao, Y., et al.: Attention-guided hierarchical structure aggregation for image matting. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13676\u201313685 (2020)","key":"23_CR30","DOI":"10.1109\/CVPR42600.2020.01369"},{"doi-asserted-by":"publisher","unstructured":"Qin, X., Dai, H., Hu, X., Fan, D.P., Shao, L., Van\u00a0Gool, L.: Highly accurate dichotomous image segmentation. In: Avidan, S., Brostow, G., Cisse, M., Farinella, G.M., Hassner, T. (eds.) European Conference on Computer Vision, pp. 38\u201356. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19797-0_3","key":"23_CR31","DOI":"10.1007\/978-3-031-19797-0_3"},{"unstructured":"Qin, X., et al.: Boundary-aware segmentation network for mobile and web applications. arXiv preprint arXiv:2101.04704 (2021)","key":"23_CR32"},{"doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10684\u201310695 (2022)","key":"23_CR33","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"23_CR34","first-page":"36479","volume":"35","author":"C Saharia","year":"2022","unstructured":"Saharia, C., et al.: Photorealistic text-to-image diffusion models with deep language understanding. Adv. Neural. Inf. Process. Syst. 35, 36479\u201336494 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"doi-asserted-by":"crossref","unstructured":"Sariyildiz, M.B., Alahari, K., Larlus, D., Kalantidis, Y.: Fake it till you make it: learning transferable representations from synthetic ImageNet clones. In: CVPR 2023\u2013IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2023)","key":"23_CR35","DOI":"10.1109\/CVPR52729.2023.00774"},{"doi-asserted-by":"crossref","unstructured":"Sauer, A., Schwarz, K., Geiger, A.: StyleGAN-XL: scaling StyleGAN to large diverse datasets. In: ACM SIGGRAPH 2022 Conference Proceedings, pp. 1\u201310 (2022)","key":"23_CR36","DOI":"10.1145\/3528233.3530738"},{"key":"23_CR37","first-page":"25278","volume":"35","author":"C Schuhmann","year":"2022","unstructured":"Schuhmann, C., et al.: LAION-5B: an open large-scale dataset for training next generation image-text models. Adv. Neural. Inf. Process. Syst. 35, 25278\u201325294 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"unstructured":"Shenoda, M., Kim, E.: DiffuGen: adaptable approach for generating labeled image datasets using stable diffusion models. arXiv preprint arXiv:2309.00248 (2023)","key":"23_CR38"},{"unstructured":"Trabucco, B., Doherty, K., Gurinas, M., Salakhutdinov, R.: Effective data augmentation with diffusion models. arXiv preprint arXiv:2302.07944 (2023)","key":"23_CR39"},{"doi-asserted-by":"crossref","unstructured":"Wang, L., et al.: Learning to detect salient objects with image-level supervision. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 136\u2013145 (2017)","key":"23_CR40","DOI":"10.1109\/CVPR.2017.404"},{"unstructured":"Wang, W., et al.: Semantic image synthesis via diffusion models. arXiv preprint arXiv:2207.00050 (2022)","key":"23_CR41"},{"doi-asserted-by":"crossref","unstructured":"Wang, Y., Qi, L., Chen, Y.C., Zhang, X., Jia, J.: Image synthesis via semantic composition. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 13749\u201313758 (2021)","key":"23_CR42","DOI":"10.1109\/ICCV48922.2021.01349"},{"doi-asserted-by":"crossref","unstructured":"Wu, W., Zhao, Y., Shou, M.Z., Zhou, H., Shen, C.: Diffumask: Synthesizing images with pixel-level annotations for semantic segmentation using diffusion models. International Conference on Computer Vision (2023)","key":"23_CR43","DOI":"10.1109\/ICCV51070.2023.00117"},{"doi-asserted-by":"crossref","unstructured":"Xu, N., Price, B., Cohen, S., Huang, T.: Deep image matting. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2970\u20132979 (2017)","key":"23_CR44","DOI":"10.1109\/CVPR.2017.41"},{"unstructured":"Yang, L., Xu, X., Kang, B., Shi, Y., Zhao, H.: FreeMask: synthetic images with dense annotations make stronger segmentation models. arXiv preprint arXiv:2310.15160 (2023)","key":"23_CR45"},{"doi-asserted-by":"crossref","unstructured":"Zeng, Y., Zhang, P., Zhang, J., Lin, Z., Lu, H.: Towards high-resolution salient object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 7234\u20137243 (2019)","key":"23_CR46","DOI":"10.1109\/ICCV.2019.00733"},{"doi-asserted-by":"crossref","unstructured":"Zhang, Y., et al.: DatasetGAN: efficient labeled data factory with minimal human effort. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10145\u201310155 (2021)","key":"23_CR47","DOI":"10.1109\/CVPR46437.2021.01001"},{"doi-asserted-by":"crossref","unstructured":"Zhu, P., Abdal, R., Femiani, J., Wonka, P.: Barbershop: GAN-based image compositing using segmentation masks. arXiv preprint arXiv:2106.01505 (2021)","key":"23_CR48","DOI":"10.1145\/3478513.3480537"}],"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\/978-3-031-73113-6_23","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,20]],"date-time":"2024-11-20T10:12:59Z","timestamp":1732097579000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73113-6_23"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,21]]},"ISBN":["9783031731129","9783031731136"],"references-count":48,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73113-6_23","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,11,21]]},"assertion":[{"value":"21 November 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"}}]}}