{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,2]],"date-time":"2025-08-02T19:07:00Z","timestamp":1754161620016,"version":"3.41.2"},"publisher-location":"Cham","reference-count":33,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031820236"},{"type":"electronic","value":"9783031820243"}],"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\/978-3-031-82024-3_21","type":"book-chapter","created":{"date-parts":[[2025,2,24]],"date-time":"2025-02-24T14:10:23Z","timestamp":1740406223000},"page":"269-281","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Combining Stable Diffusion and\u00a0Object Detection for\u00a0Semi-automatic Environment Decoration"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-6281-1729","authenticated-orcid":false,"given":"Philipp","family":"Drescher","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0749-1186","authenticated-orcid":false,"given":"Irena","family":"Ruprecht","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3842-5349","authenticated-orcid":false,"given":"Volker","family":"Settgast","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,2,25]]},"reference":[{"key":"21_CR1","unstructured":"AUTOMATIC1111: Stable diffusion web UI. https:\/\/github.com\/AUTOMATIC1111\/stable-diffusion-webui"},{"key":"21_CR2","doi-asserted-by":"crossref","unstructured":"Canny, J.: A computational approach to edge detection. IEEE Trans. Pattern Anal. Mach. Intell. PAMI-8, 679\u2013698 (1986)","DOI":"10.1109\/TPAMI.1986.4767851"},{"key":"21_CR3","unstructured":"Chang, A.X., et al.: ShapeNet: an information-rich 3D model repository. Tech. rep., Stanford University \u2014 Princeton University \u2014 Toyota Technological Institute at Chicago (2015)"},{"key":"21_CR4","doi-asserted-by":"crossref","unstructured":"Chen, R., Chen, Y., Jiao, N., Jia, K.: Fantasia3D: disentangling geometry and appearance for high-quality text-to-3D content creation. In: IEEE\/CVF International Conference on Computer Vision (2023)","DOI":"10.1109\/ICCV51070.2023.02033"},{"key":"21_CR5","doi-asserted-by":"crossref","unstructured":"Collins, J., et al.: ABO: dataset and benchmarks for real-world 3D object understanding. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2022)","DOI":"10.1109\/CVPR52688.2022.02045"},{"key":"21_CR6","doi-asserted-by":"crossref","unstructured":"Coyne, B., Sproat, R.: WordsEye: an automatic text-to-scene conversion system. In: Proceedings of the 28th annual conference on Computer graphics and interactive techniques (2001)","DOI":"10.1145\/383259.383316"},{"key":"21_CR7","doi-asserted-by":"crossref","unstructured":"Deitke, M., et al.: Objaverse-XL: a universe of 10M+ 3D objects. In: Conference on Neural Information Processing Systems (2024)","DOI":"10.1109\/CVPR52729.2023.01263"},{"key":"21_CR8","unstructured":"Glover, C.J., Anderson, E.F.: D.A.V.E: a prototype for automatic environment decoration. In: Eurographics 2019 (2019)"},{"key":"21_CR9","doi-asserted-by":"crossref","unstructured":"Glushakov, M., Zhang, Y., Han, Y., Scargill, T.J., Lan, G., Gorlatova, M.: Edge-based provisioning of holographic content for contextual and personalized augmented reality. In: IEEE International Conference on Pervasive Computing and Communications Workshops (2020)","DOI":"10.1109\/PerComWorkshops48775.2020.9156256"},{"key":"21_CR10","unstructured":"Guo, Y., et al.: Decorate3D: text-driven high-quality texture generation for mesh decoration in the wild. In: Conference on Neural Information Processing Systems (2024)"},{"key":"21_CR11","doi-asserted-by":"crossref","unstructured":"Haque, A., Tancik, M., Efros, A., Holynski, A., Kanazawa, A.: Instruct-NeRF2NeRF: editing 3D scenes with instructions. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (2023)","DOI":"10.1109\/ICCV51070.2023.01808"},{"key":"21_CR12","doi-asserted-by":"crossref","unstructured":"H\u00f6llein, L., Cao, A., Owens, A., Johnson, J., Nie\u00dfner, M.: Text2room: extracting textured 3D meshes from 2D text-to-image models. In: IEEE\/CVF International Conference on Computer Vision (2023)","DOI":"10.1109\/ICCV51070.2023.00727"},{"key":"21_CR13","unstructured":"Jocher, G., Chaurasia, A., Qiu, J.: Ultralytics YOLOv8. https:\/\/github.com\/ultralytics\/ultralytics"},{"key":"21_CR14","doi-asserted-by":"crossref","unstructured":"Ju, X., Huang, Z., Li, Y., Zhang, G., Qiao, Y., Li, H.: DiffindScene: diffusion-based high-quality 3D indoor scene generation (2023)","DOI":"10.1109\/CVPR52733.2024.00433"},{"key":"21_CR15","doi-asserted-by":"crossref","unstructured":"K\u00e1n, P., Kaufmann, H.: Automatic furniture arrangement using greedy cost minimization. In: IEEE Conference on Virtual Reality and 3D User Interfaces (2018)","DOI":"10.1109\/VR.2018.8448291"},{"key":"21_CR16","doi-asserted-by":"crossref","unstructured":"Kawar, B., et al.: Imagic: text-based real image editing with diffusion models. In: Proceedings - 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2023)","DOI":"10.1109\/CVPR52729.2023.00582"},{"issue":"7","key":"21_CR17","doi-asserted-by":"publisher","first-page":"1956","DOI":"10.1007\/s11263-020-01316-z","volume":"128","author":"A Kuznetsova","year":"2020","unstructured":"Kuznetsova, A., et al.: The open images dataset V4. Int. J. Comput. Vis. 128(7), 1956\u20131981 (2020). https:\/\/doi.org\/10.1007\/s11263-020-01316-z","journal-title":"Int. J. Comput. Vis."},{"key":"21_CR18","doi-asserted-by":"crossref","unstructured":"Lee, H., Savva, M., Chang, A.X.: Text-to-3D shape generation. Comput. Graph. Forum 43, e15061 (2024)","DOI":"10.1111\/cgf.15061"},{"key":"21_CR19","unstructured":"Michel, O., Bhattad, A., VanderBilt, E., Krishna, R., Kembhavi, A., Gupta, T.: OBJECT 3DIT: language-guided 3D-aware image editing. In: Thirty-seventh Conference on Neural Information Processing Systems (2023)"},{"key":"21_CR20","unstructured":"Mikubill: WebUI extension for ControlNet. https:\/\/github.com\/Mikubill\/sd-webui-controlnet"},{"key":"21_CR21","doi-asserted-by":"crossref","unstructured":"Ranftl, R., Lasinger, K., Hafner, D., Schindler, K., Koltun, V.: Towards robust monocular depth estimation: Mixing datasets for zero-shot cross-dataset transfer. IEEE Trans. Pattern Anal. Mach. Intell. 44, 1623\u20131637(2022)","DOI":"10.1109\/TPAMI.2020.3019967"},{"key":"21_CR22","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: unified, real-time object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2016)","DOI":"10.1109\/CVPR.2016.91"},{"key":"21_CR23","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\/Computer Vision Foundation (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"21_CR24","doi-asserted-by":"crossref","unstructured":"Smith, G., Stuerzlinger, W., Salzman, T.: 3D scene manipulation with 2D devices and constraints. In: Proceedings of the Graphics Interface 2001 Conference (2001)","DOI":"10.1007\/978-1-4471-0337-0_4"},{"key":"21_CR25","doi-asserted-by":"crossref","unstructured":"Weiss, T., Yildiz, I., Agarwal, N., Ataer-Cansizoglu, E., Choi, J.W.: Image-driven furniture style for interactive 3D scene modeling. In: Computer Graphics Forum (2020)","DOI":"10.1111\/cgf.14126"},{"key":"21_CR26","unstructured":"Xu, K., Stewart, J., Fiume, E.: Constraint-based automatic placement for scene composition. In: Proceedings of the Graphics Interface 2002 Conference (2002)"},{"key":"21_CR27","doi-asserted-by":"crossref","unstructured":"Yang, B., et al.: Paint by example: exemplar-based image editing with diffusion models. arXiv preprint arXiv:2211.13227 (2022)","DOI":"10.1109\/CVPR52729.2023.01763"},{"key":"21_CR28","doi-asserted-by":"crossref","unstructured":"Yu, L.F., Yeung, S.K., Tang, C.K., Terzopoulos, D., Chan, T.F., Osher, S.J.: Make it home: automatic optimization of furniture arrangement. ACM Transactions on Graphics (TOG)-Proceedings of ACM SIGGRAPH 2011 (2011)","DOI":"10.1145\/1964921.1964981"},{"key":"21_CR29","doi-asserted-by":"crossref","unstructured":"Yu, L.F., Yeung, S.K., Terzopoulos, D.: The Clutterpalette: an interactive tool for detailing indoor scenes. IEEE Trans. Vis. Comput. Graph. 22, 1138\u20131148 (2016)","DOI":"10.1109\/TVCG.2015.2417575"},{"key":"21_CR30","doi-asserted-by":"crossref","unstructured":"Zhang, L., Rao, A., Agrawala, M.: Adding conditional control to text-to-image diffusion models. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (2023)","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"21_CR31","doi-asserted-by":"crossref","unstructured":"Zhang, S., Han, Z., Zhang, H.: User guided 3D scene enrichment. In: Proceedings of the 15th ACM SIGGRAPH Conference on Virtual-Reality Continuum and its Applications in Industry (2016)","DOI":"10.1145\/3013971.3014002"},{"key":"21_CR32","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Han, L., Ghosh, A., Metaxas, D., Ren, J.: SINE: SINgle image editing with text-to-image diffusion models. In: Proceedings - 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2023)","DOI":"10.1109\/CVPR52729.2023.00584"},{"key":"21_CR33","doi-asserted-by":"crossref","unstructured":"Zhuang, J., Wang, C., Liu, L., Lin, L., Li, G.: DreamEditor: text-driven 3D scene editing with neural fields. arXiv preprint arXiv:2306.13455 (2023)","DOI":"10.1145\/3610548.3618190"}],"container-title":["Lecture Notes in Computer Science","Advances in Computer Graphics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-82024-3_21","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,29]],"date-time":"2025-07-29T04:24:21Z","timestamp":1753763061000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-82024-3_21"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9783031820236","9783031820243"],"references-count":33,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-82024-3_21","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"25 February 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"CGI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Computer Graphics International Conference","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Geneva","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Switzerland","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":"1 July 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 July 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"41","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"cgi2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.cgs-network.org\/cgi24\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}