{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T15:39:28Z","timestamp":1778081968729,"version":"3.51.4"},"publisher-location":"Cham","reference-count":80,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031729324","type":"print"},{"value":"9783031729331","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,10,3]],"date-time":"2024-10-03T00:00:00Z","timestamp":1727913600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,3]],"date-time":"2024-10-03T00:00:00Z","timestamp":1727913600000},"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\/978-3-031-72933-1_4","type":"book-chapter","created":{"date-parts":[[2024,10,2]],"date-time":"2024-10-02T12:02:53Z","timestamp":1727870573000},"page":"52-70","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":12,"title":["AnyHome: Open-Vocabulary Generation of\u00a0Structured and\u00a0Textured 3D Homes"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0115-0831","authenticated-orcid":false,"given":"Rao","family":"Fu","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0003-7385-3397","authenticated-orcid":false,"given":"Zehao","family":"Wen","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0005-6344-2425","authenticated-orcid":false,"given":"Zichen","family":"Liu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4663-3324","authenticated-orcid":false,"given":"Srinath","family":"Sridhar","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,10,3]]},"reference":[{"key":"4_CR1","unstructured":"Achlioptas, P., Diamanti, O., Mitliagkas, I., Guibas, L.: Learning representations and generative models for 3D point clouds. In: International Conference on Machine Learning, pp. 40\u201349. PMLR (2018)"},{"key":"4_CR2","doi-asserted-by":"crossref","unstructured":"Bahmani, S., et al.: CC3D: layout-conditioned generation of compositional 3D scenes. arXiv preprint arXiv:2303.12074 (2023)","DOI":"10.1109\/ICCV51070.2023.00659"},{"key":"4_CR3","unstructured":"Bautista, M.A., et al.: GAUDI: a neural architect for immersive 3D scene generation. In: Advances in Neural Information Processing Systems, vol. 35, pp. 25102\u201325116 (2022)"},{"key":"4_CR4","doi-asserted-by":"crossref","unstructured":"Bisht, S., Shekhawat, K., Upasani, N., Jain, R.N., Tiwaskar, R.J., Hebbar, C.: Transforming an adjacency graph into dimensioned floorplan layouts. In: Computer Graphics Forum, vol.\u00a041, pp. 5\u201322. Wiley Online Library (2022)","DOI":"10.1111\/cgf.14451"},{"key":"4_CR5","doi-asserted-by":"crossref","unstructured":"Cao, T., Kreis, K., Fidler, S., Sharp, N., Yin, K.: Texfusion: synthesizing 3D textures with text-guided image diffusion models. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4169\u20134181 (2023)","DOI":"10.1109\/ICCV51070.2023.00385"},{"key":"4_CR6","unstructured":"Chang, A.X., Eric, M., Savva, M., Manning, C.D.: Sceneseer: 3D scene design with natural language. arXiv preprint arXiv:1703.00050 (2017)"},{"key":"4_CR7","doi-asserted-by":"crossref","unstructured":"Chen, D.Z., Siddiqui, Y., Lee, H.Y., Tulyakov, S., Nie\u00dfner, M.: Text2tex: text-driven texture synthesis via diffusion models. arXiv preprint arXiv:2303.11396 (2023)","DOI":"10.1109\/ICCV51070.2023.01701"},{"key":"4_CR8","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"100","DOI":"10.1007\/978-3-030-20893-6_7","volume-title":"Computer Vision \u2013 ACCV 2018","author":"K Chen","year":"2019","unstructured":"Chen, K., Choy, C.B., Savva, M., Chang, A.X., Funkhouser, T., Savarese, S.: Text2Shape: generating shapes from natural language by learning joint embeddings. In: Jawahar, C.V., Li, H., Mori, G., Schindler, K. (eds.) ACCV 2018. LNCS, vol. 11363, pp. 100\u2013116. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-20893-6_7"},{"key":"4_CR9","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. arXiv preprint arXiv:2303.13873 (2023)","DOI":"10.1109\/ICCV51070.2023.02033"},{"issue":"6","key":"4_CR10","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3550454.3555447","volume":"41","author":"Z Chen","year":"2022","unstructured":"Chen, Z., Wang, G., Liu, Z.: Text2light: zero-shot text-driven HDR panorama generation. ACM Trans. Graph. (TOG) 41(6), 1\u201316 (2022)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"4_CR11","doi-asserted-by":"crossref","unstructured":"Cheng, Y.C., Lee, H.Y., Tulyakov, S., Schwing, A.G., Gui, L.Y.: SDFusion: multimodal 3D shape completion, reconstruction, and generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4456\u20134465 (2023)","DOI":"10.1109\/CVPR52729.2023.00433"},{"key":"4_CR12","doi-asserted-by":"crossref","unstructured":"Deitke, M., et al.: Objaverse: a universe of annotated 3D objects. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13142\u201313153 (2023)","DOI":"10.1109\/CVPR52729.2023.01263"},{"key":"4_CR13","unstructured":"Deitke, M., et al.: ProcTHOR: large-scale embodied AI using procedural generation. In: Advances in Neural Information Processing Systems, vol. 35, pp. 5982\u20135994 (2022)"},{"key":"4_CR14","unstructured":"Feng, W., et al.: LayoutGPT: compositional visual planning and generation with large language models. arXiv preprint arXiv:2305.15393 (2023)"},{"issue":"6","key":"4_CR15","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/2366145.2366154","volume":"31","author":"M Fisher","year":"2012","unstructured":"Fisher, M., Ritchie, D., Savva, M., Funkhouser, T., Hanrahan, P.: Example-based synthesis of 3D object arrangements. ACM Trans. Graph. (TOG) 31(6), 1\u201311 (2012)","journal-title":"ACM Trans. Graph. (TOG)"},{"issue":"6","key":"4_CR16","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/2816795.2818057","volume":"34","author":"M Fisher","year":"2015","unstructured":"Fisher, M., Savva, M., Li, Y., Hanrahan, P., Nie\u00dfner, M.: Activity-centric scene synthesis for functional 3D scene modeling. ACM Trans. Graph. (TOG) 34(6), 1\u201313 (2015)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"4_CR17","unstructured":"Fridman, R., Abecasis, A., Kasten, Y., Dekel, T.: Scenescape: text-driven consistent scene generation. arXiv preprint arXiv:2302.01133 (2023)"},{"key":"4_CR18","doi-asserted-by":"crossref","unstructured":"Fu, H., et\u00a0al.: 3D-front: 3D furnished rooms with layouts and semantics. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10933\u201310942 (2021)","DOI":"10.1109\/ICCV48922.2021.01075"},{"key":"4_CR19","doi-asserted-by":"crossref","unstructured":"Fu, H., et al.: 3D-future: 3D furniture shape with texture. Int. J. Comput. Vis. 1\u201325 (2021)","DOI":"10.1007\/s11263-021-01534-z"},{"issue":"6","key":"4_CR20","first-page":"1","volume":"36","author":"Q Fu","year":"2017","unstructured":"Fu, Q., Chen, X., Wang, X., Wen, S., Zhou, B., Fu, H.: Adaptive synthesis of indoor scenes via activity-associated object relation graphs. ACM Trans. Graph. (TOG) 36(6), 1\u201313 (2017)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"4_CR21","unstructured":"Fu, R., Zhan, X., Chen, Y., Ritchie, D., Sridhar, S.: ShapeCrafter: a recursive text-conditioned 3D shape generation model. In: Advances in Neural Information Processing Systems, vol. 35, pp. 8882\u20138895 (2022)"},{"key":"4_CR22","doi-asserted-by":"crossref","unstructured":"Gibson, J.J.: The Ecological Approach to Visual Perception: Classic Edition. Psychology Press (2014)","DOI":"10.4324\/9781315740218"},{"key":"4_CR23","doi-asserted-by":"crossref","unstructured":"Giudice, N.A.: 15. Navigating without vision: principles of blind spatial cognition. Handbook of behavioral and cognitive geography, p.\u00a0260 (2018)","DOI":"10.4337\/9781784717544.00024"},{"key":"4_CR24","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. arXiv preprint arXiv:2303.11989 (2023)","DOI":"10.1109\/ICCV51070.2023.00727"},{"key":"4_CR25","doi-asserted-by":"crossref","unstructured":"Hu, R., Huang, Z., Tang, Y., Van Kaick, O., Zhang, H., Huang, H.: Graph2Plan: learning floorplan generation from layout graphs. ACM Trans. Graph. (TOG) 39(4), 118-1 (2020)","DOI":"10.1145\/3386569.3392391"},{"key":"4_CR26","unstructured":"Huang, I., Krishna, V., Atekha, O., Guibas, L.: Aladdin: zero-shot hallucination of stylized 3D assets from abstract scene descriptions. arXiv preprint arXiv:2306.06212 (2023)"},{"key":"4_CR27","doi-asserted-by":"crossref","unstructured":"Hwang, I., Kim, H., Kim, Y.M.: Text2Scene: text-driven indoor scene stylization with part-aware details. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1890\u20131899 (2023)","DOI":"10.1109\/CVPR52729.2023.00188"},{"key":"4_CR28","doi-asserted-by":"crossref","unstructured":"Jain, A., Mildenhall, B., Barron, J.T., Abbeel, P., Poole, B.: Zero-shot text-guided object generation with dream fields (2022)","DOI":"10.1109\/CVPR52688.2022.00094"},{"key":"4_CR29","unstructured":"Jun, H., Nichol, A.: Shap-E: generating conditional 3D implicit functions. arXiv preprint arXiv:2305.02463 (2023)"},{"key":"4_CR30","doi-asserted-by":"crossref","unstructured":"Khanna, M., et al.: Habitat synthetic scenes dataset (HSSD-200): an analysis of 3D scene scale and realism tradeoffs for objectgoal navigation. arXiv preprint arXiv:2306.11290 (2023)","DOI":"10.1109\/CVPR52733.2024.01550"},{"key":"4_CR31","unstructured":"Li, J., Li, D., Savarese, S., Hoi, S.: Blip-2: bootstrapping language-image pre-training with frozen image encoders and large language models. arXiv preprint arXiv:2301.12597 (2023)"},{"issue":"2","key":"4_CR32","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3303766","volume":"38","author":"M Li","year":"2019","unstructured":"Li, M., et al.: Grains: generative recursive autoencoders for indoor scenes. ACM Trans. Graph. (TOG) 38(2), 1\u201316 (2019)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"4_CR33","doi-asserted-by":"crossref","unstructured":"Lin, C.H., et al.: Magic3D: high-resolution text-to-3D content creation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 300\u2013309 (2023)","DOI":"10.1109\/CVPR52729.2023.00037"},{"key":"4_CR34","doi-asserted-by":"crossref","unstructured":"Liu, Z., Wang, Y., Qi, X., Fu, C.W.: Towards implicit text-guided 3D shape generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 17896\u201317906 (2022)","DOI":"10.1109\/CVPR52688.2022.01737"},{"issue":"2","key":"4_CR35","doi-asserted-by":"publisher","first-page":"335","DOI":"10.1037\/0278-7393.28.2.335","volume":"28","author":"JM Loomis","year":"2002","unstructured":"Loomis, J.M., Lippa, Y., Klatzky, R.L., Golledge, R.G.: Spatial updating of locations specified by 3-D sound and spatial language. J. Exp. Psychol. Learn. Mem. Cogn. 28(2), 335 (2002)","journal-title":"J. Exp. Psychol. Learn. Mem. Cogn."},{"key":"4_CR36","doi-asserted-by":"publisher","DOI":"10.1016\/j.autcon.2022.104470","volume":"142","author":"Z Luo","year":"2022","unstructured":"Luo, Z., Huang, W.: FloorplanGAN: vector residential floorplan adversarial generation. Autom. Constr. 142, 104470 (2022)","journal-title":"Autom. Constr."},{"key":"4_CR37","doi-asserted-by":"crossref","unstructured":"Ma, C., Vining, N., Lefebvre, S., Sheffer, A.: Game level layout from design specification. In: Computer Graphics Forum, vol.\u00a033, pp. 95\u2013104. Wiley Online Library (2014)","DOI":"10.1111\/cgf.12314"},{"key":"4_CR38","doi-asserted-by":"crossref","unstructured":"Ma, Y., et al.: X-mesh: towards fast and accurate text-driven 3D stylization via dynamic textual guidance. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 2749\u20132760 (2023)","DOI":"10.1109\/ICCV51070.2023.00258"},{"key":"4_CR39","doi-asserted-by":"crossref","unstructured":"Merrell, P., Schkufza, E., Koltun, V.: Computer-generated residential building layouts. In: ACM SIGGRAPH Asia 2010 Papers, pp. 1\u201312 (2010)","DOI":"10.1145\/1882261.1866203"},{"issue":"4","key":"4_CR40","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/2010324.1964982","volume":"30","author":"P Merrell","year":"2011","unstructured":"Merrell, P., Schkufza, E., Li, Z., Agrawala, M., Koltun, V.: Interactive furniture layout using interior design guidelines. ACM Trans. Graph. (TOG) 30(4), 1\u201310 (2011)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"4_CR41","doi-asserted-by":"crossref","unstructured":"Mittal, P., Cheng, Y.C., Singh, M., Tulsiani, S.: AutoSDF: shape priors for 3D completion, reconstruction and generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 306\u2013315 (2022)","DOI":"10.1109\/CVPR52688.2022.00040"},{"key":"4_CR42","doi-asserted-by":"crossref","unstructured":"Mohammad\u00a0Khalid, N., Xie, T., Belilovsky, E., Popa, T.: Clip-mesh: generating textured meshes from text using pretrained image-text models. In: SIGGRAPH Asia 2022 Conference Papers, pp.\u00a01\u20138 (2022)","DOI":"10.1145\/3550469.3555392"},{"key":"4_CR43","doi-asserted-by":"crossref","unstructured":"M\u00fcller, P., Wonka, P., Haegler, S., Ulmer, A., Van\u00a0Gool, L.: Procedural modeling of buildings. In: ACM SIGGRAPH 2006 Papers, pp. 614\u2013623 (2006)","DOI":"10.1145\/1141911.1141931"},{"key":"4_CR44","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"162","DOI":"10.1007\/978-3-030-58452-8_10","volume-title":"Computer Vision \u2013 ECCV 2020","author":"N Nauata","year":"2020","unstructured":"Nauata, N., Chang, K.-H., Cheng, C.-Y., Mori, G., Furukawa, Y.: House-GAN: relational generative adversarial networks for graph-constrained house layout generation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 162\u2013177. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_10"},{"key":"4_CR45","doi-asserted-by":"crossref","unstructured":"Nauata, N., Hosseini, S., Chang, K.H., Chu, H., Cheng, C.Y., Furukawa, Y.: House-GAN++: generative adversarial layout refinement network towards intelligent computational agent for professional architects. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13632\u201313641 (2021)","DOI":"10.1109\/CVPR46437.2021.01342"},{"key":"4_CR46","unstructured":"Nichol, A., Jun, H., Dhariwal, P., Mishkin, P., Chen, M.: Point-e: a system for generating 3D point clouds from complex prompts. arXiv preprint arXiv:2212.08751 (2022)"},{"key":"4_CR47","unstructured":"OpenAI: GPT-4 technical report (2023)"},{"key":"4_CR48","unstructured":"Paschalidou, D., Kar, A., Shugrina, M., Kreis, K., Geiger, A., Fidler, S.: ATISS: autoregressive transformers for indoor scene synthesis. In: Advances in Neural Information Processing Systems, vol. 34, pp. 12013\u201312026 (2021)"},{"issue":"4","key":"4_CR49","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/2601097.2601164","volume":"33","author":"CH Peng","year":"2014","unstructured":"Peng, C.H., Yang, Y.L., Wonka, P.: Computing layouts with deformable templates. ACM Trans. Graph. (TOG) 33(4), 1\u201311 (2014)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"4_CR50","unstructured":"Pick, H.L.: Visual coding of nonvisual spatial information (1974)"},{"key":"4_CR51","unstructured":"Poole, B., Jain, A., Barron, J.T., Mildenhall, B.: Dreamfusion: text-to-3D using 2D diffusion. arXiv preprint arXiv:2209.14988 (2022)"},{"key":"4_CR52","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"155","DOI":"10.1007\/978-3-030-58586-0_10","volume-title":"Computer Vision \u2013 ECCV 2020","author":"P Purkait","year":"2020","unstructured":"Purkait, P., Zach, C., Reid, I.: SG-VAE: scene grammar variational autoencoder to generate new indoor scenes. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12369, pp. 155\u2013171. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58586-0_10"},{"key":"4_CR53","doi-asserted-by":"crossref","unstructured":"Qi, S., Zhu, Y., Huang, S., Jiang, C., Zhu, S.C.: Human-centric indoor scene synthesis using stochastic grammar. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5899\u20135908 (2018)","DOI":"10.1109\/CVPR.2018.00618"},{"key":"4_CR54","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"4_CR55","doi-asserted-by":"crossref","unstructured":"Reimers, N., Gurevych, I.: Sentence-BERT: sentence embeddings using Siamese BERT-networks (2019). http:\/\/arxiv.org\/abs\/1908.10084","DOI":"10.18653\/v1\/D19-1410"},{"key":"4_CR56","doi-asserted-by":"crossref","unstructured":"Richardson, E., Metzer, G., Alaluf, Y., Giryes, R., Cohen-Or, D.: Texture: text-guided texturing of 3D shapes. arXiv preprint arXiv:2302.01721 (2023)","DOI":"10.1145\/3588432.3591503"},{"key":"4_CR57","doi-asserted-by":"crossref","unstructured":"Sanghi, A., Chu, H., Lambourne, J.G., Wang, Y.A.R.: Clip-forge: towards zero-shot text-to-shape generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18603\u201318613 (2022)","DOI":"10.1109\/CVPR52688.2022.01805"},{"key":"4_CR58","doi-asserted-by":"crossref","unstructured":"Sanghi, A., et al.: Clip-sculptor: zero-shot generation of high-fidelity and diverse shapes from natural language. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18339\u201318348 (2023)","DOI":"10.1109\/CVPR52729.2023.01759"},{"key":"4_CR59","doi-asserted-by":"crossref","unstructured":"Shabani, M.A., Hosseini, S., Furukawa, Y.: Housediffusion: vector floorplan generation via a diffusion model with discrete and continuous denoising. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5466\u20135475 (2023)","DOI":"10.1109\/CVPR52729.2023.00529"},{"key":"4_CR60","doi-asserted-by":"crossref","unstructured":"Song, L., et al.: Roomdreamer: text-driven 3D indoor scene synthesis with coherent geometry and texture. arXiv preprint arXiv:2305.11337 (2023)","DOI":"10.1145\/3581783.3611800"},{"issue":"4","key":"4_CR61","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3528223.3530135","volume":"41","author":"J Sun","year":"2022","unstructured":"Sun, J., Wu, W., Liu, L., Min, W., Zhang, G., Zheng, L.: WallPlan: synthesizing floorplans by learning to generate wall graphs. ACM Trans. Graph. (TOG) 41(4), 1\u201314 (2022)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"4_CR62","doi-asserted-by":"crossref","unstructured":"Tang, H., et al.: Graph transformer GANs for graph-constrained house generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2173\u20132182 (2023)","DOI":"10.1109\/CVPR52729.2023.00216"},{"key":"4_CR63","doi-asserted-by":"crossref","unstructured":"Tang, J., Nie, Y., Markhasin, L., Dai, A., Thies, J., Nie\u00dfner, M.: Diffuscene: scene graph denoising diffusion probabilistic model for generative indoor scene synthesis. arXiv preprint arXiv:2303.14207 (2023)","DOI":"10.1109\/CVPR52733.2024.01938"},{"key":"4_CR64","unstructured":"Tang, S., Zhang, F., Chen, J., Wang, P., Furukawa, Y.: Mvdiffusion: enabling holistic multi-view image generation with correspondence-aware diffusion. arXiv preprint arXiv:2307.01097 (2023)"},{"issue":"4","key":"4_CR65","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3306346.3322941","volume":"38","author":"K Wang","year":"2019","unstructured":"Wang, K., Lin, Y.A., Weissmann, B., Savva, M., Chang, A.X., Ritchie, D.: Planit: planning and instantiating indoor scenes with relation graph and spatial prior networks. ACM Trans. Graph. (TOG) 38(4), 1\u201315 (2019)","journal-title":"ACM Trans. Graph. (TOG)"},{"issue":"4","key":"4_CR66","first-page":"1","volume":"37","author":"K Wang","year":"2018","unstructured":"Wang, K., Savva, M., Chang, A.X., Ritchie, D.: Deep convolutional priors for indoor scene synthesis. ACM Trans. Graph. (TOG) 37(4), 1\u201314 (2018)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"4_CR67","doi-asserted-by":"crossref","unstructured":"Wang, X., Yeshwanth, C., Nie\u00dfner, M.: SceneFormer: indoor scene generation with transformers. In: 2021 International Conference on 3D Vision (3DV), pp. 106\u2013115. IEEE (2021)","DOI":"10.1109\/3DV53792.2021.00021"},{"key":"4_CR68","unstructured":"Wang, Z., et al.: ProlificDreamer: high-fidelity and diverse text-to-3D generation with variational score distillation. arXiv preprint arXiv:2305.16213 (2023)"},{"key":"4_CR69","unstructured":"Wei, J., et al.: Emergent abilities of large language models. Trans. Mach. Learn. Res. (2022). https:\/\/openreview.net\/forum?id=yzkSU5zdwD, Survey Certification"},{"key":"4_CR70","doi-asserted-by":"crossref","unstructured":"Wei, J., Wang, H., Feng, J., Lin, G., Yap, K.H.: Taps3D: text-guided 3D textured shape generation from pseudo supervision. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16805\u201316815 (2023)","DOI":"10.1109\/CVPR52729.2023.01612"},{"key":"4_CR71","doi-asserted-by":"crossref","unstructured":"Wei, Q.A., et al.: Lego-net: learning regular rearrangements of objects in rooms. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 19037\u201319047 (2023)","DOI":"10.1109\/CVPR52729.2023.01825"},{"key":"4_CR72","doi-asserted-by":"crossref","unstructured":"Wu, W., Fu, X.M., Tang, R., Wang, Y., Qi, Y.H., Liu, L.: Data-driven interior plan generation for residential buildings. ACM Trans. Graph. (SIGGRAPH Asia) 38(6) (2019)","DOI":"10.1145\/3355089.3356556"},{"issue":"4","key":"4_CR73","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/2461912.2461968","volume":"32","author":"K Xu","year":"2013","unstructured":"Xu, K., Chen, K., Fu, H., Sun, W.L., Hu, S.M.: Sketch2Scene: sketch-based co-retrieval and co-placement of 3D models. ACM Trans. Graph. (TOG) 32(4), 1\u201315 (2013)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"4_CR74","doi-asserted-by":"crossref","unstructured":"Yang, M.J., Guo, Y.X., Zhou, B., Tong, X.: Indoor scene generation from a collection of semantic-segmented depth images. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 15203\u201315212 (2021)","DOI":"10.1109\/ICCV48922.2021.01492"},{"key":"4_CR75","doi-asserted-by":"crossref","unstructured":"Yang, Y., et\u00a0al.: Holodeck: language guided generation of 3D embodied AI environments. In: The IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2024), vol.\u00a030, pp. 20\u201325. IEEE\/CVF (2024)","DOI":"10.1109\/CVPR52733.2024.01536"},{"key":"4_CR76","doi-asserted-by":"crossref","unstructured":"Yeshwanth, C., Liu, Y.C., Nie\u00dfner, M., Dai, A.: ScanNet++: a high-fidelity dataset of 3D indoor scenes. In: Proceedings of the International Conference on Computer Vision (ICCV) (2023)","DOI":"10.1109\/ICCV51070.2023.00008"},{"key":"4_CR77","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 Trans. Graph. (TOG)-Proceedings of ACM SIGGRAPH 2011, Article no. 86 30(4) (2011)","DOI":"10.1145\/2010324.1964981"},{"key":"4_CR78","unstructured":"Zhai, G., et al.: Commonscenes: generating commonsense 3D indoor scenes with scene graphs. arXiv preprint arXiv:2305.16283 (2023)"},{"issue":"2","key":"4_CR79","first-page":"1","volume":"39","author":"Z Zhang","year":"2020","unstructured":"Zhang, Z., et al.: Deep generative modeling for scene synthesis via hybrid representations. ACM Trans. Graph. (TOG) 39(2), 1\u201321 (2020)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"4_CR80","unstructured":"Zhao, W.X., et\u00a0al.: A survey of large language models. arXiv preprint arXiv:2303.18223 (2023)"}],"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\/978-3-031-72933-1_4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,2]],"date-time":"2024-10-02T12:32:21Z","timestamp":1727872341000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72933-1_4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,3]]},"ISBN":["9783031729324","9783031729331"],"references-count":80,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72933-1_4","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,3]]},"assertion":[{"value":"3 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"}}]}}