{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,25]],"date-time":"2025-04-25T19:10:08Z","timestamp":1745608208192,"version":"3.40.4"},"publisher-location":"Singapore","reference-count":48,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819658114","type":"print"},{"value":"9789819658121","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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\/978-981-96-5812-1_13","type":"book-chapter","created":{"date-parts":[[2025,4,25]],"date-time":"2025-04-25T18:44:44Z","timestamp":1745606684000},"page":"234-252","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Concept-Edge Fusion: Background Generation for\u00a0Product Presentation Based on\u00a0Text-to-Image Model"],"prefix":"10.1007","author":[{"given":"Pengfei","family":"Deng","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tianjiao","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weize","family":"Quan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hanyu","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qinglin","family":"Lu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhifeng","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dong-Ming","family":"Yan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,4,26]]},"reference":[{"key":"13_CR1","first-page":"2256","volume":"37","author":"J Sohl-Dickstein","year":"2015","unstructured":"Sohl-Dickstein, J., Weiss, E.A., Maheswaranathan, N., Ganguli, S.: Deep unsupervised learning using nonequilibrium thermodynamics. Int. Conf. Mach. Learn. 37, 2256\u20132265 (2015)","journal-title":"Int. Conf. Mach. Learn."},{"key":"13_CR2","first-page":"6840","volume":"33","author":"J Ho","year":"2020","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. Neural Inf. Process. Syst. 33, 6840\u20136851 (2020)","journal-title":"Neural Inf. Process. Syst."},{"key":"13_CR3","doi-asserted-by":"publisher","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10674\u201310685 (2022). https:\/\/doi.org\/10.1109\/CVPR52688.2022.01042","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"13_CR4","first-page":"16784","volume":"162","author":"AQ Nichol","year":"2022","unstructured":"Nichol, A.Q., et al.: GLIDE: towards photorealistic image generation and editing with text-guided diffusion models. Int. Conf. Mach. Learn. 162, 16784\u201316804 (2022)","journal-title":"Int. Conf. Mach. Learn."},{"key":"13_CR5","unstructured":"Ramesh, A., Dhariwal, P., Nichol, A., Chu, C., Chen, M.: Hierarchical text-conditional image generation with clip latents. arXiv preprintarXiv:2204.06125, 1(2), 3 (2022)"},{"key":"13_CR6","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. Neural Inf. Process. Syst. 35, 36479\u201336494 (2022)","journal-title":"Neural Inf. Process. Syst."},{"key":"13_CR7","unstructured":"Balaji, Y., et al.: Ediffi: text-to-image diffusion models with an ensemble of expert denoisers. arXiv preprintarXiv:2211.01324 (2022)"},{"key":"13_CR8","unstructured":"Chen, X., Huang, L., Liu, Y., Shen, Y., Zhao, D., Zhao, H.: AnyDoor: zero-shot object-level image customization. arXiv preprintarXiv:2307.09481 (2023)"},{"issue":"4","key":"13_CR9","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3592116","volume":"42","author":"H Chefer","year":"2023","unstructured":"Chefer, H., Alaluf, Y., Vinker, Y., Wolf, L., Cohen-Or, D.: Attend-and-excite: attention-based semantic guidance for text-to-image diffusion models. ACM Trans. Graph. 42(4), 1\u201310 (2023)","journal-title":"ACM Trans. Graph."},{"issue":"4","key":"13_CR10","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3592450","volume":"42","author":"O Avrahami","year":"2023","unstructured":"Avrahami, O., Fried, O., Lischinski, D.: Blended latent diffusion. ACM Trans. Graph. 42(4), 1\u201311 (2023)","journal-title":"ACM Trans. Graph."},{"key":"13_CR11","first-page":"21548","volume":"202","author":"Z Liu","year":"2023","unstructured":"Liu, Z., et al.: Cones: concept neurons in diffusion models for customized generation. Int. Conf. Mach. Learn. 202, 21548\u201321566 (2023)","journal-title":"Int. Conf. Mach. Learn."},{"key":"13_CR12","unstructured":"Liu, Z., et al.: Cones 2: customizable Image Synthesis with Multiple Subjects. arXiv preprintarXiv:2305.19327 (2023)"},{"key":"13_CR13","doi-asserted-by":"publisher","unstructured":"Ruiz, N., Li, Y., Jampani, V., Pritch, Y., Rubinstein, M., Aberman, K.: DreamBooth: fine tuning text-to-image diffusion models for subject-driven generation. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 22500\u201322510 (2023). https:\/\/doi.org\/10.1109\/CVPR52729.2023.02155","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"13_CR14","unstructured":"Elarabawy, A., Kamath, H., Denton, S.: Direct inversion: optimization-free text-driven real image editing with diffusion models. arXiv preprintarXiv:2211.07825 (2022)"},{"key":"13_CR15","doi-asserted-by":"publisher","unstructured":"Wei, Y., Zhang, Y., Ji, Z., Bai, J., Zhang, L., Zuo, W.: ELITE: encoding visual concepts into textual embeddings for customized text-to-image generation. In: IEEE\/CVF International Conference on Computer Vision, pp. 15897\u201315907 (2022). https:\/\/doi.org\/10.1109\/ICCV51070.2023.01461","DOI":"10.1109\/ICCV51070.2023.01461"},{"key":"13_CR16","doi-asserted-by":"publisher","unstructured":"Brooks, T., Holynski, A., Efros, A.A.: InstructPix2Pix: learning to follow image editing instructions. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18392\u201318402 (2023). https:\/\/doi.org\/10.1109\/CVPR52729.2023.01764","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"13_CR17","unstructured":"Ye, H., Zhang, J., Liu, S., Han, X., Yang, W.: Ip-adapter: text compatible image prompt adapter for text-to-image diffusion models. arXiv preprintarXiv:2308.06721 (2023)"},{"key":"13_CR18","unstructured":"Zhang, B., et al.: Controlcom: controllable image composition using diffusion model. arXiv preprintarXiv:2308.10040 (2023)"},{"key":"13_CR19","doi-asserted-by":"publisher","unstructured":"Song, Y., et al.: ObjectStitch: object compositing with diffusion model. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18310\u201318319 (2023). https:\/\/doi.org\/10.1109\/CVPR52729.2023.01756","DOI":"10.1109\/CVPR52729.2023.01756"},{"key":"13_CR20","doi-asserted-by":"crossref","unstructured":"Zhang, L., Rao, A., Agrawala, M.: Adding conditional control to text-to-image diffusion models. In: 2023 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 3813\u20133824 (2023)","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"13_CR21","doi-asserted-by":"crossref","unstructured":"Quan, W., Chen, J., Liu, Y., Yan, D.M., Wonka, P.: Deep learning-based image and video inpainting: a survey 132(7), 2367\u20132400 (2024)","DOI":"10.1007\/s11263-023-01977-6"},{"key":"13_CR22","unstructured":"Couairon, G., Verbeek, J., Schwenk, H., Cord, M.: DiffEdit: diffusion-based semantic image editing with mask guidance. In: International Conference on Learning Representations (2023)"},{"key":"13_CR23","doi-asserted-by":"publisher","unstructured":"Lugmayr, A., Danelljan, M., Romero, A., Yu, F., Timofte, R., Van\u00a0Gool, L.: RePaint: inpainting using denoising diffusion probabilistic models. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11451\u201311461 (2022). https:\/\/doi.org\/10.1109\/CVPR52688.2022.01117","DOI":"10.1109\/CVPR52688.2022.01117"},{"key":"13_CR24","doi-asserted-by":"publisher","unstructured":"Yang, B., et al.: Paint by example: exemplar-based image editing with diffusion models. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18381\u201318391 (2023). https:\/\/doi.org\/10.1109\/CVPR52729.2023.01763","DOI":"10.1109\/CVPR52729.2023.01763"},{"key":"13_CR25","doi-asserted-by":"publisher","unstructured":"Xie, S., Zhang, Z., Lin, Z., Hinz, T., Zhang, K.: SmartBrush: text and shape guided object inpainting with diffusion model. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 22428\u201322437 (2023). https:\/\/doi.org\/10.1109\/CVPR52729.2023.02148","DOI":"10.1109\/CVPR52729.2023.02148"},{"key":"13_CR26","doi-asserted-by":"crossref","unstructured":"Voynov, A., Aberman, K., Cohen-Or, D.: Sketch-guided text-to-image diffusion models. In: ACM SIGGRAPH (2023)","DOI":"10.1145\/3588432.3591560"},{"key":"13_CR27","unstructured":"Vandersanden, J., Holl, S., Huang, X., Singh, G.: Edge-preserving noise for diffusion models. arXiv (2024)"},{"key":"13_CR28","unstructured":"Yu, T., et al.: Inpaint anything: segment anything meets image inpainting. arXiv preprintarXiv:2304.06790 (2023)"},{"key":"13_CR29","doi-asserted-by":"publisher","unstructured":"Kirillov, A., et al.: Segment anything. In: IEEE\/CVF International Conference on Computer Vision, pp. 3992\u20134003 (2023). https:\/\/doi.org\/10.1109\/ICCV51070.2023.00371","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"13_CR30","unstructured":"Chen, H., et al.: Disenbooth: identity-preserving disentangled tuning for subject-driven text-to-image generation. In: International Conference on Learning Representations (2023)"},{"key":"13_CR31","doi-asserted-by":"publisher","unstructured":"Mokady, R., Hertz, A., Aberman, K., Pritch, Y., Cohen-Or, D.: Null-text inversion for editing real images using guided diffusion models. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6038\u20136047 (2023). https:\/\/doi.org\/10.1109\/CVPR52729.2023.00585","DOI":"10.1109\/CVPR52729.2023.00585"},{"key":"13_CR32","unstructured":"Voynov, A., Chu, Q., Cohen-Or, D., Aberman, K.: $$ P+ $$: extended textual conditioning in text-to-image generation. arXiv preprintarXiv:2303.09522 (2023)"},{"key":"13_CR33","unstructured":"Gal, R., et al.: An image is worth one word: personalizing text-to-image generation using textual inversion. In: International Conference on Learning Representations (2023)"},{"key":"13_CR34","unstructured":"Jia, X., et al.: Taming encoder for zero fine-tuning image customization with text-to-image diffusion models. arXiv preprintarXiv:2304.02642 (2023)"},{"key":"13_CR35","unstructured":"Xiao, G., Yin, T., Freeman, W.T., Durand, F., Han, S.: FastComposer: tuning-free multi-subject image generation with localized attention. arXiv preprintarXiv:2305.10431 (2023)"},{"key":"13_CR36","unstructured":"Hertz, A., Mokady, R., Tenenbaum, J., Aberman, K., Pritch, Y., Cohen-Or, D.: Prompt-to-prompt image editing with cross-attention control. In: International Conference on Learning Representations (2023)"},{"issue":"4","key":"13_CR37","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/1778765.1778862","volume":"29","author":"K Sunkavalli","year":"2010","unstructured":"Sunkavalli, K., Johnson, M.K., Matusik, W., Pfister, H.: Multi-scale image harmonization. ACM Trans. Graph. 29(4), 1\u201310 (2010)","journal-title":"ACM Trans. Graph."},{"key":"13_CR38","doi-asserted-by":"crossref","unstructured":"Chen, H., et al.: Hierarchical dynamic image harmonization. In: ACM International Conference on Multimedia, pp. 1422\u20131430 (2023)","DOI":"10.1145\/3581783.3611747"},{"key":"13_CR39","doi-asserted-by":"crossref","unstructured":"Xue, B., Ran, S., Chen, Q., Jia, R., Zhao, B., Tang, X.: Dccf: deep comprehensible color filter learning framework for high-resolution image harmonization. In: European Conference on Computer Vision, pp. 300\u2013316 (2022)","DOI":"10.1007\/978-3-031-20071-7_18"},{"key":"13_CR40","doi-asserted-by":"publisher","unstructured":"Chen, B.C., Kae, A.: Toward realistic image compositing with adversarial learning. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8407\u20138416 (2019). https:\/\/doi.org\/10.1109\/CVPR.2019.00861","DOI":"10.1109\/CVPR.2019.00861"},{"key":"13_CR41","doi-asserted-by":"publisher","unstructured":"Cong, W., et al.: DoveNet: deep image harmonization via domain verification. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8391\u20138400 (2020). https:\/\/doi.org\/10.1109\/CVPR42600.2020.00842","DOI":"10.1109\/CVPR42600.2020.00842"},{"key":"13_CR42","doi-asserted-by":"publisher","unstructured":"Cong, W., Tao, X., Niu, L., Liang, J., Gao, X., Sun, Q., Zhang, L:. High-resolution image harmonization via collaborative dual transformations. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18449\u201318458 (2022). https:\/\/doi.org\/10.1109\/CVPR52688.2022.01792","DOI":"10.1109\/CVPR52688.2022.01792"},{"key":"13_CR43","doi-asserted-by":"publisher","unstructured":"Guo, Z., Zheng, H., Jiang, Y., Gu, Z., Zheng, B.: Intrinsic image harmonization. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16362\u201316371 (2021). https:\/\/doi.org\/10.1109\/CVPR46437.2021.01610","DOI":"10.1109\/CVPR46437.2021.01610"},{"key":"13_CR44","doi-asserted-by":"publisher","unstructured":"Wang, S., et al.: Advancing and evaluating text-guided image inpainting. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18359\u201318369 (2023). https:\/\/doi.org\/10.1109\/CVPR52729.2023.01761","DOI":"10.1109\/CVPR52729.2023.01761"},{"key":"13_CR45","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning. In: Neural Information Processing Systems (2023)"},{"key":"13_CR46","unstructured":"Kirstain, Y., Polyak, A., Singer, U., Matiana, S., Penna, J., Levy, O.: Pick-a-pic: an open dataset of user preferences for text-to-image generation (2023)"},{"key":"13_CR47","doi-asserted-by":"publisher","unstructured":"Yi, R., Tian, H., Gu, Z., Lai, Y.K., Rosin, P.L.: Towards artistic image aesthetics assessment: a large-scale dataset and a new method. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 22388\u201322397 (2023). https:\/\/doi.org\/10.1109\/CVPR52729.2023.02144","DOI":"10.1109\/CVPR52729.2023.02144"},{"key":"13_CR48","unstructured":"Wang, H., Yu, Y., Luo, T., Fan, H., Zhang, L.: MaGIC: multi-modality guided image completion (2024)"}],"container-title":["Lecture Notes in Computer Science","Computational Visual Media"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-5812-1_13","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,25]],"date-time":"2025-04-25T18:44:58Z","timestamp":1745606698000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-5812-1_13"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819658114","9789819658121"],"references-count":48,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-5812-1_13","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"26 April 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"CVM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Computational Visual Media","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Hong Kong SAR","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19 April 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21 April 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"cvm2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/iccvm.org\/2025\/index.htm","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}