{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,4]],"date-time":"2026-04-04T17:43:12Z","timestamp":1775324592798,"version":"3.50.1"},"publisher-location":"Cham","reference-count":62,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031726637","type":"print"},{"value":"9783031726644","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T00:00:00Z","timestamp":1729900800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T00:00:00Z","timestamp":1729900800000},"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\/978-3-031-72664-4_10","type":"book-chapter","created":{"date-parts":[[2024,10,25]],"date-time":"2024-10-25T17:02:04Z","timestamp":1729875724000},"page":"167-184","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":14,"title":["EchoScene: Indoor Scene Generation via\u00a0Information Echo Over\u00a0Scene Graph Diffusion"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6702-8302","authenticated-orcid":false,"given":"Guangyao","family":"Zhai","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1023-2852","authenticated-orcid":false,"given":"Evin P\u0131nar","family":"\u00d6rnek","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3883-1905","authenticated-orcid":false,"given":"Dave Zhenyu","family":"Chen","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0003-1924-6502","authenticated-orcid":false,"given":"Ruotong","family":"Liao","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0671-8323","authenticated-orcid":false,"given":"Yan","family":"Di","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6032-5611","authenticated-orcid":false,"given":"Nassir","family":"Navab","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5598-5212","authenticated-orcid":false,"given":"Federico","family":"Tombari","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0620-5774","authenticated-orcid":false,"given":"Benjamin","family":"Busam","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,10,26]]},"reference":[{"key":"10_CR1","doi-asserted-by":"crossref","unstructured":"Bahmani, S., et al.: CC3D: layout-conditioned generation of compositional 3D scenes. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00659"},{"key":"10_CR2","unstructured":"Bautista, M.A., et\u00a0al.: Gaudi: a neural architect for immersive 3D scene generation. In: NeurIPS (2022)"},{"key":"10_CR3","unstructured":"Bi\u0144kowski, M., Sutherland, D.J., Arbel, M., Gretton, A.: Demystifying MMD GANs. In: ICLR (2018)"},{"key":"10_CR4","doi-asserted-by":"crossref","unstructured":"Brooks, T., Holynski, A., Efros, A.A.: InstructPix2Pix: learning to follow image editing instructions. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"10_CR5","doi-asserted-by":"crossref","unstructured":"Chang, A., Monroe, W., Savva, M., Potts, C., Manning, C.D.: Text to 3D scene generation with rich lexical grounding. In: ACL (2015)","DOI":"10.3115\/v1\/W14-2404"},{"key":"10_CR6","doi-asserted-by":"crossref","unstructured":"Chang, A., Savva, M., Manning, C.D.: Learning spatial knowledge for text to 3D scene generation. In: EMNLP (2014)","DOI":"10.3115\/v1\/D14-1217"},{"key":"10_CR7","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TPAMI.2021.3137605","volume":"45","author":"X Chang","year":"2021","unstructured":"Chang, X., Ren, P., Xu, P., Li, Z., Chen, X., Hauptmann, A.: A comprehensive survey of scene graphs: generation and application. T-PAMI 45, 1\u201326 (2021)","journal-title":"T-PAMI"},{"key":"10_CR8","doi-asserted-by":"crossref","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. In: SIGGRAPH (2023)","DOI":"10.1145\/3592116"},{"key":"10_CR9","doi-asserted-by":"crossref","unstructured":"Chen, D.Z., Li, H., Lee, H.Y., Tulyakov, S., Nie\u00dfner, M.: SceneTex: high-quality texture synthesis for indoor scenes via diffusion priors. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.01992"},{"key":"10_CR10","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. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.01701"},{"key":"10_CR11","doi-asserted-by":"crossref","unstructured":"Chen, Z., Wang, G., Liu, Z.: SceneDreamer: unbounded 3D scene generation from 2d image collections. T-PAMI (2023)","DOI":"10.1109\/TPAMI.2023.3321857"},{"key":"10_CR12","doi-asserted-by":"crossref","unstructured":"Cheng, Y.C., Lee, H.Y., Tuyakov, S., Schwing, A., Gui, L.: SDFusion: multimodal 3D shape completion, reconstruction, and generation. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00433"},{"key":"10_CR13","doi-asserted-by":"crossref","unstructured":"Cohen-Bar, D., Richardson, E., Metzer, G., Giryes, R., Cohen-Or, D.: Set-the-Scene: global-local training for generating controllable nerf scenes. In: ICCV Workshop (2023)","DOI":"10.1109\/ICCVW60793.2023.00314"},{"key":"10_CR14","doi-asserted-by":"crossref","unstructured":"Dhamo, H., et al.: Semantic image manipulation using scene graphs. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00526"},{"key":"10_CR15","doi-asserted-by":"crossref","unstructured":"Dhamo, H., Manhardt, F., Navab, N., Tombari, F.: Graph-to-3D: end-to-end generation and manipulation of 3D scenes using scene graphs. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.01604"},{"key":"10_CR16","doi-asserted-by":"crossref","unstructured":"Fu, H., et\u00a0al.: 3D-FRONT: 3D furnished rooms with layouts and semantics. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.01075"},{"key":"10_CR17","doi-asserted-by":"crossref","unstructured":"Gao, G., Liu, W., Chen, A., Geiger, A., Sch\u00f6lkopf, B.: GraphDreamer: compositional 3D scene synthesis from scene graphs. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.02012"},{"key":"10_CR18","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 (2017)"},{"key":"10_CR19","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. In: NeurIPS (2020)"},{"key":"10_CR20","doi-asserted-by":"crossref","unstructured":"Johnson, J., Gupta, A., Fei-Fei, L.: Image generation from scene graphs. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00133"},{"key":"10_CR21","doi-asserted-by":"crossref","unstructured":"Johnson, J., et al.: Image retrieval using scene graphs. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298990"},{"key":"10_CR22","doi-asserted-by":"crossref","unstructured":"Jyothi, A.A., Durand, T., He, J., Sigal, L., Mori, G.: LayoutVAE: stochastic scene layout generation from a label set. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00999"},{"key":"10_CR23","unstructured":"Kenton, J.D.M.W.C., Toutanova, L.K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: NAACL-HLT (2019)"},{"key":"10_CR24","unstructured":"Kong, L., Cui, J., Sun, H., Zhuang, Y., Prakash, B.A., Zhang, C.: Autoregressive diffusion model for graph generation. In: ICML (2023)"},{"key":"10_CR25","doi-asserted-by":"crossref","unstructured":"Kong, X., Liu, S., Lyu, X., Taher, M., Qi, X., Davison, A.J.: Eschernet: a generative model for scalable view synthesis. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.00908"},{"key":"10_CR26","doi-asserted-by":"crossref","unstructured":"Kong, X., et al.: Semantic graph based place recognition for 3D point clouds. In: IROS (2020)","DOI":"10.1109\/IROS45743.2020.9341060"},{"key":"10_CR27","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1007\/s11263-016-0981-7","volume":"123","author":"R Krishna","year":"2017","unstructured":"Krishna, R., et al.: Visual genome: connecting language and vision using crowdsourced dense image annotations. IJCV 123, 32\u201373 (2017)","journal-title":"IJCV"},{"key":"10_CR28","unstructured":"Kynk\u00e4\u00e4nniemi, T., Karras, T., Aittala, M., Aila, T., Lehtinen, J.: The role of imagenet classes in fr\u00e9chet inception distance. In: ICLR (2023)"},{"key":"10_CR29","first-page":"1","volume":"38","author":"M Li","year":"2019","unstructured":"Li, M., et al.: GRAINS: generative recursive autoencoders for indoor scenes. TOG 38, 1\u201316 (2019)","journal-title":"TOG"},{"key":"10_CR30","doi-asserted-by":"crossref","unstructured":"Li, M., Duan, Y., Zhou, J., Lu, J.: Diffusion-SDF: text-to-shape via voxelized diffusion. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01216"},{"key":"10_CR31","doi-asserted-by":"crossref","unstructured":"Li, X., Zhang, Y., Ye, X.: DrivingDiffusion: layout-guided multi-view driving scene video generation with latent diffusion model (2023)","DOI":"10.1007\/978-3-031-73229-4_27"},{"key":"10_CR32","unstructured":"Lin, C., Mu, Y.: InstructScene: instruction-driven 3D indoor scene synthesis with semantic graph prior. In: ICLR (2024)"},{"key":"10_CR33","unstructured":"Lin, Y., et al.: CompoNeRF: text-guided multi-object compositional nerf with editable 3D scene layout (2023)"},{"key":"10_CR34","doi-asserted-by":"crossref","unstructured":"Liu, R., Wu, R., Van\u00a0Hoorick, B., Tokmakov, P., Zakharov, S., Vondrick, C.: Zero-1-to-3: zero-shot one image to 3D object. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00853"},{"key":"10_CR35","unstructured":"Liu, Z., Feng, Y., Black, M.J., Nowrouzezahrai, D., Paull, L., Liu, W.: MeshDiffusion: score-based generative 3D mesh modeling. In: ICLR (2023)"},{"key":"10_CR36","doi-asserted-by":"crossref","unstructured":"Luo, A., Zhang, Z., Wu, J., Tenenbaum, J.B.: End-to-end optimization of scene layout. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00381"},{"key":"10_CR37","first-page":"1","volume":"37","author":"R Ma","year":"2018","unstructured":"Ma, R., et al.: Language-driven synthesis of 3D scenes from scene databases. TOG 37, 1\u201316 (2018)","journal-title":"TOG"},{"key":"10_CR38","unstructured":"Mandlekar, A., et al.: MimicGen: a data generation system for scalable robot learning using human demonstrations. In: CoRL (2023)"},{"key":"10_CR39","unstructured":"Meng, C., et al.: SDEdit: guided image synthesis and editing with stochastic differential equations. In: ICLR (2022)"},{"key":"10_CR40","doi-asserted-by":"crossref","unstructured":"\u00d6zsoy, E., \u00d6rnek, E.P., Eck, U., Tombari, F., Navab, N.: Multimodal semantic scene graphs for holistic modeling of surgical procedures. In: Arxiv (2021)","DOI":"10.1007\/978-3-031-16449-1_45"},{"key":"10_CR41","doi-asserted-by":"crossref","unstructured":"Park, J.J., Florence, P., Straub, J., Newcombe, R., Lovegrove, S.: DeepSDF: learning continuous signed distance functions for shape representation. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00025"},{"key":"10_CR42","unstructured":"Paschalidou, D., Kar, A., Shugrina, M., Kreis, K., Geiger, A., Fidler, S.: ATISS: autoregressive transformers for indoor scene synthesis. In: NeurIPS (2021)"},{"key":"10_CR43","doi-asserted-by":"crossref","unstructured":"Po, R., Wetzstein, G.: Compositional 3D scene generation using locally conditioned diffusion. In: 3DV (2023)","DOI":"10.1109\/3DV62453.2024.00026"},{"key":"10_CR44","unstructured":"Poole, B., Jain, A., Barron, J.T., Mildenhall, B.: DreamFusion: text-to-3D using 2d diffusion. In: ICLR (2023)"},{"key":"10_CR45","unstructured":"Pronovost, E., et al.: Scenario diffusion: controllable driving scenario generation with diffusion. In: NeurIPS (2023)"},{"key":"10_CR46","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":"10_CR47","doi-asserted-by":"crossref","unstructured":"Rosinol, A., Gupta, A., Abate, M., Shi, J., Carlone, L.: 3D dynamic scene graphs: actionable spatial perception with places, objects, and humans. In: RSS (2020)","DOI":"10.15607\/RSS.2020.XVI.079"},{"key":"10_CR48","unstructured":"Shi, Y., Wang, P., Ye, J., Mai, L., Li, K., Yang, X.: MVDream: multi-view diffusion for 3D generation. In: ICLR (2024)"},{"key":"10_CR49","doi-asserted-by":"crossref","unstructured":"Simsar, E., Tonioni, A., \u00d6rnek, E.P., Tombari, F.: LatentSwap3D: semantic edits on 3D image gans. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) Workshops, pp. 2899\u20132909 (2023)","DOI":"10.1109\/ICCVW60793.2023.00312"},{"key":"10_CR50","unstructured":"Sohl-Dickstein, J., Weiss, E., Maheswaranathan, N., Ganguli, S.: Deep unsupervised learning using nonequilibrium thermodynamics. In: ICML (2015)"},{"key":"10_CR51","unstructured":"Song, Y., Ermon, S.: Generative modeling by estimating gradients of the data distribution. Adv. Neural Inf. Process. Syst. 32 (2019)"},{"key":"10_CR52","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":"10_CR53","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. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.01938"},{"key":"10_CR54","unstructured":"Verma, T., De, A., Agrawal, Y., Vinay, V., Chakrabarti, S.: VarScene: a deep generative model for realistic scene graph synthesis. In: ICML (2022)"},{"key":"10_CR55","unstructured":"Vignac, C., Krawczuk, I., Siraudin, A., Wang, B., Cevher, V., Frossard, P.: DiGress: discrete denoising diffusion for graph generation. In: International Conference on Learning Representations (ICLR) (2023)"},{"key":"10_CR56","doi-asserted-by":"crossref","unstructured":"Wald, J., Dhamo, H., Navab, N., Tombari, F.: Learning 3D semantic scene graphs from 3D indoor reconstructions. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00402"},{"key":"10_CR57","doi-asserted-by":"crossref","unstructured":"Zhai, G., et al.: SG-bot: object rearrangement via coarse-to-fine robotic imagination on scene graphs. In: ICRA (2024)","DOI":"10.1109\/ICRA57147.2024.10610792"},{"key":"10_CR58","unstructured":"Zhai, G., et al.: CommonScenes: generating commonsense 3D indoor scenes with scene graphs. In: NeurIPS (2023)"},{"key":"10_CR59","doi-asserted-by":"crossref","unstructured":"Zhang, L., Rao, A., Agrawala, M.: Adding conditional control to text-to-image diffusion models. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"10_CR60","unstructured":"Zhou, X., et al.: GALA3D: towards text-to-3D complex scene generation via layout-guided generative gaussian splatting (2024)"},{"key":"10_CR61","doi-asserted-by":"crossref","unstructured":"Zhou, Y., While, Z., Kalogerakis, E.: SceneGraphNet: neural message passing for 3D indoor scene augmentation. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00748"},{"key":"10_CR62","doi-asserted-by":"publisher","first-page":"475","DOI":"10.1007\/978-3-031-16449-1_45","volume-title":"MICCAI 2022","author":"E \u00d6zsoy","year":"2022","unstructured":"\u00d6zsoy, E., \u00d6rnek, E.P., Eck, U., Czempiel, T., Tombari, F., Navab, N.: 4D-OR: Semantic scene graphs for or domain modeling. In: Wang, L., Dou, Q., Fletcher, P.T., Speidel, S., Li, S. (eds.) MICCAI 2022, vol. 13437, pp. 475\u2013485. Springer, Heidelberg (2022). https:\/\/doi.org\/10.1007\/978-3-031-16449-1_45"}],"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\/978-3-031-72664-4_10","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,25]],"date-time":"2024-10-25T17:04:54Z","timestamp":1729875894000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72664-4_10"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,26]]},"ISBN":["9783031726637","9783031726644"],"references-count":62,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72664-4_10","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,26]]},"assertion":[{"value":"26 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"}}]}}