{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,24]],"date-time":"2026-10-24T11:45:00Z","timestamp":1792842300516,"version":"4.5.0"},"publisher-location":"Cham","reference-count":75,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031726972","type":"print"},{"value":"9783031726989","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\/978-3-031-72698-9_15","type":"book-chapter","created":{"date-parts":[[2024,10,25]],"date-time":"2024-10-25T00:45:57Z","timestamp":1729817157000},"page":"251-268","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":19,"title":["FOREST2SEQ: Revitalizing Order Prior for\u00a0Sequential Indoor Scene Synthesis"],"prefix":"10.1007","author":[{"given":"Qi","family":"Sun","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hang","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wengang","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Li","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Houqiang","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,10,26]]},"reference":[{"key":"15_CR1","unstructured":"https:\/\/www.ikea.com\/pt\/en\/customer-service\/services\/planning-consultation"},{"key":"15_CR2","unstructured":"Bengio, Y., Ducharme, R., Vincent, P.: A neural probabilistic language model. In: NeurIPS (2000)"},{"key":"15_CR3","doi-asserted-by":"crossref","unstructured":"Bundy, A., Wallen, L.: Breadth-first search. In: Catalogue of Artificial Intelligence Tools (1984)","DOI":"10.1007\/978-3-642-96868-6"},{"key":"15_CR4","doi-asserted-by":"crossref","unstructured":"Chang, A., et al.: Matterport3D: learning from RGB-D data in indoor environments. In: 3DV (2017)","DOI":"10.1109\/3DV.2017.00081"},{"key":"15_CR5","unstructured":"Chang, H., et\u00a0al.: Muse: text-to-image generation via masked generative transformers. arXiv preprint arXiv:2301.00704 (2023)"},{"key":"15_CR6","doi-asserted-by":"crossref","unstructured":"Chang, H., Zhang, H., Jiang, L., Liu, C., Freeman, W.T.: MaskGiT: masked generative image transformer. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01103"},{"key":"15_CR7","doi-asserted-by":"crossref","unstructured":"Chaudhuri, S., Kalogerakis, E., Giguere, S., Funkhouser, T.: Attribit: content creation with semantic attributes. In: UIST (2013)","DOI":"10.1145\/2501988.2502008"},{"key":"15_CR8","doi-asserted-by":"crossref","unstructured":"Currey, A., Heafield, K.: Unsupervised source hierarchies for low-resource neural machine translation. In: ACL (2018)","DOI":"10.18653\/v1\/W17-4715"},{"key":"15_CR9","unstructured":"Deitke, M., et al.: ProcTHOR: large-scale embodied AI using procedural generation. In: NeurIPS (2022)"},{"key":"15_CR10","doi-asserted-by":"crossref","unstructured":"Devaranjan, J., Kar, A., Fidler, S.: Meta-sim2: unsupervised learning of scene structure for synthetic data generation. In: ECCV (2020)","DOI":"10.1007\/978-3-030-58520-4_42"},{"key":"15_CR11","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: NAACL (2019)"},{"key":"15_CR12","unstructured":"Dosovitskiy, Aet\u00a0al.: An image is worth 16$$\\times $$16 words: transformers for image recognition at scale. In: ICLR (2021)"},{"key":"15_CR13","doi-asserted-by":"crossref","unstructured":"Eriguchi, A., Hashimoto, K., Tsuruoka, Y.: Tree-to-sequence attentional neural machine translation. In: ACL (2016)","DOI":"10.18653\/v1\/P16-1078"},{"key":"15_CR14","doi-asserted-by":"crossref","unstructured":"Esser, P., Rombach, R., Ommer, B.: Taming transformers for high-resolution image synthesis. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"15_CR15","unstructured":"Ester, M., Kriegel, H.P., Sander, J., Xu, X., et\u00a0al.: A density-based algorithm for discovering clusters in large spatial databases with noise. In: KDD (1996)"},{"key":"15_CR16","unstructured":"Feng, W., et al.: LayoutGPT: compositional visual planning and generation with large language models. arXiv preprint arXiv:2305.15393 (2023)"},{"key":"15_CR17","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 TOG 31, 1\u201311 (2012)","journal-title":"ACM TOG"},{"key":"15_CR18","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 TOG 34, 1\u201313 (2015)","journal-title":"ACM TOG"},{"key":"15_CR19","doi-asserted-by":"crossref","unstructured":"Fu, H., et\u00a0al.: 3D-FRONT: 3D furnished rooms with layouts and semantics. In: CVPR (2021)","DOI":"10.1109\/ICCV48922.2021.01075"},{"key":"15_CR20","doi-asserted-by":"publisher","first-page":"3313","DOI":"10.1007\/s11263-021-01534-z","volume":"129","author":"H Fu","year":"2021","unstructured":"Fu, H., et al.: 3D-FUTURE: 3D furniture shape with texture. IJCV 129, 3313\u20133337 (2021)","journal-title":"IJCV"},{"key":"15_CR21","unstructured":"Fu, Z., et al.: Decoder-only or encoder-decoder? interpreting language model as a regularized encoder-decoder. arXiv preprint arXiv:2304.04052 (2023)"},{"key":"15_CR22","unstructured":"Gani, H., Naseer, M., Yaqub, M.: How to train vision transformer on small-scale datasets? In: BMVC (2022)"},{"key":"15_CR23","doi-asserted-by":"publisher","first-page":"8902","DOI":"10.1109\/TPAMI.2023.3237577","volume":"45","author":"L Gao","year":"2023","unstructured":"Gao, L., Sun, J.M., Mo, K., Lai, Y.K., Guibas, L.J., Yang, J.: SceneHGN: hierarchical graph networks for 3d indoor scene generation with fine-grained geometry. IEEE TPAMI 45, 8902\u20138919 (2023)","journal-title":"IEEE TPAMI"},{"key":"15_CR24","doi-asserted-by":"crossref","unstructured":"Gu, S., et al.: Vector quantized diffusion model for text-to-image synthesis. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01043"},{"key":"15_CR25","doi-asserted-by":"crossref","unstructured":"He, K., Chen, X., Xie, S., Li, Y., Doll\u00e1r, P., Girshick, R.: Masked autoencoders are scalable vision learners. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"15_CR26","unstructured":"Henderson, P., Subr, K., Ferrari, V.: Automatic generation of constrained furniture layouts. arXiv preprint arXiv:1711.10939 (2017)"},{"key":"15_CR27","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":"15_CR28","doi-asserted-by":"crossref","unstructured":"Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. (1997)","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"15_CR29","doi-asserted-by":"crossref","unstructured":"Iyer, S., Konstas, I., Cheung, A., Zettlemoyer, L.: Summarizing source code using a neural attention model. In: ACL (2016)","DOI":"10.18653\/v1\/P16-1195"},{"key":"15_CR30","unstructured":"Jiang, Y., Lim, M., Saxena, A.: Learning object arrangements in 3D scenes using human context. arXiv preprint arXiv:1206.6462 (2012)"},{"key":"15_CR31","doi-asserted-by":"crossref","unstructured":"Kar, A., et al.: Meta-sim: learning to generate synthetic datasets. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00465"},{"key":"15_CR32","unstructured":"Ke, G., He, D., Liu, T.Y.: Rethinking positional encoding in language pre-training. arXiv preprint arXiv:2006.15595 (2020)"},{"key":"15_CR33","doi-asserted-by":"crossref","unstructured":"Koh, J.Y., et al.: Simple and effective synthesis of indoor 3d scenes. In: AAAI (2023)","DOI":"10.1609\/aaai.v37i1.25199"},{"key":"15_CR34","unstructured":"Lee, J., Lee, Y., Kim, J., Kosiorek, A., Choi, S., Teh, Y.W.: Set transformer: a framework for attention-based permutation-invariant neural networks. In: ICML (2019)"},{"key":"15_CR35","doi-asserted-by":"crossref","unstructured":"Leimer, K., Guerrero, P., Weiss, T., Musialski, P.: Layoutenhancer: generating good indoor layouts from imperfect data. In: SIGGRAPH Asia (2022)","DOI":"10.1145\/3550469.3555425"},{"key":"15_CR36","doi-asserted-by":"crossref","unstructured":"Lewis, M., et al.: BART: denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension. In: ACL (2020)","DOI":"10.18653\/v1\/2020.acl-main.703"},{"key":"15_CR37","first-page":"1","volume":"38","author":"M Li","year":"2019","unstructured":"Li, M., et al.: GRAINS: generative recursive autoencoders for indoor scenes. ACM TOG 38, 1\u201316 (2019)","journal-title":"ACM TOG"},{"key":"15_CR38","unstructured":"Li, R., et\u00a0al.: StarCoder: may the source be with you! arXiv preprint arXiv:2305.06161 (2023)"},{"key":"15_CR39","unstructured":"Liu, J., et\u00a0al.: CLIP-Layout: Style-consistent indoor scene synthesis with semantic furniture embedding. arXiv preprint arXiv:2303.03565 (2023)"},{"key":"15_CR40","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. In: ICLR (2019)"},{"key":"15_CR41","doi-asserted-by":"crossref","unstructured":"Ma, R., Li, H., Zou, C., Liao, Z., Tong, X., Zhang, H.: Action-driven 3D indoor scene evolution. ACM TOG 35, 173-1 (2016)","DOI":"10.1145\/2980179.2980223"},{"key":"15_CR42","first-page":"1","volume":"37","author":"R Ma","year":"2018","unstructured":"Ma, R., et al.: Language-driven synthesis of 3D scenes from scene databases. ACM TOG 37, 1\u201316 (2018)","journal-title":"ACM TOG"},{"key":"15_CR43","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 TOG 30, 1\u201310 (2011)","journal-title":"ACM TOG"},{"key":"15_CR44","unstructured":"OpenAI: GPT-4 technical report. arXiv preprint arXiv:2303.08774 (2023)"},{"key":"15_CR45","unstructured":"Ouyang, L., et\u00a0al.: Training language models to follow instructions with human feedback. In: NeurIPS (2022)"},{"key":"15_CR46","doi-asserted-by":"crossref","unstructured":"Para, W.R., Guerrero, P., Mitra, N., Wonka, P.: COFS: controllable furniture layout synthesis. In: SIGGRAPH (2023)","DOI":"10.1145\/3588432.3591561"},{"key":"15_CR47","unstructured":"Paschalidou, D., Kar, A., Shugrina, M., Kreis, K., Geiger, A., Fidler, S.: ATISS: autoregressive transformers for indoor scene synthesis. In: NeurIPS (2021)"},{"key":"15_CR48","doi-asserted-by":"crossref","unstructured":"Patil, A.G., Patil, S.G., Li, M., Fisher, M., Savva, M., Zhang, H.: Advances in data-driven analysis and synthesis of 3D indoor scenes. Comput. Graph Forum (2023)","DOI":"10.1111\/cgf.14927"},{"key":"15_CR49","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: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00618"},{"key":"15_CR50","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: ICML (2021)"},{"key":"15_CR51","unstructured":"Radford, A., Wu, J., Child, R., Luan, D., Amodei, D., Sutskever, I.: Language models are unsupervised multitask learners. In: ICML (2019)"},{"key":"15_CR52","doi-asserted-by":"crossref","unstructured":"Rezatofighi, H., Tsoi, N., Gwak, J., Sadeghian, A., Reid, I., Savarese, S.: Generalized intersection over union: a metric and a loss for bounding box regression. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00075"},{"key":"15_CR53","doi-asserted-by":"crossref","unstructured":"Ritchie, D., Wang, K., Lin, Y.a.: Fast and flexible indoor scene synthesis via deep convolutional generative models. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00634"},{"key":"15_CR54","unstructured":"Rubenstein, P.K., et\u00a0al.: AudioPaLM: a large language model that can speak and listen. arXiv preprint arXiv:2306.12925 (2023)"},{"key":"15_CR55","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/2897824.2925867","volume":"30","author":"M Savva","year":"2016","unstructured":"Savva, M., Chang, A.X., Hanrahan, P., Fisher, M., Nie\u00dfner, M.: PiGraphs: learning interaction snapshots from observations. ACM TOG 30, 1\u201310 (2016)","journal-title":"ACM TOG"},{"key":"15_CR56","doi-asserted-by":"crossref","unstructured":"Shaw, P., Uszkoreit, J., Vaswani, A.: Self-attention with relative position representations. arXiv preprint arXiv:1803.02155 (2018)","DOI":"10.18653\/v1\/N18-2074"},{"key":"15_CR57","unstructured":"Socher, R., Lin, C.C.Y., Ng, A.Y., Manning, C.D.: Parsing natural scenes and natural language with recursive neural networks. In: ICML (2011)"},{"key":"15_CR58","unstructured":"Straub, J., et\u00a0al.: The replica dataset: a digital replica of indoor spaces. arXiv preprint arXiv:1906.05797 (2019)"},{"key":"15_CR59","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":"15_CR60","doi-asserted-by":"crossref","unstructured":"Tang, K., Zhang, H., Wu, B., Luo, W., Liu, W.: Learning to compose dynamic tree structures for visual contexts. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00678"},{"key":"15_CR61","unstructured":"Vaswani, A., et al.: Attention is all you need. In: NeurIPS (2017)"},{"key":"15_CR62","unstructured":"Vinyals, O., Bengio, S., Kudlur, M.: Order matters: sequence to sequence for sets. In: ICLR (2016)"},{"key":"15_CR63","first-page":"1","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 TOG 38, 1\u201315 (2019)","journal-title":"ACM TOG"},{"key":"15_CR64","doi-asserted-by":"crossref","unstructured":"Wang, X., Yeshwanth, C., Nie\u00dfner, M.: SceneFormer: indoor scene generation with transformers. In: 3DV (2021)","DOI":"10.1109\/3DV53792.2021.00021"},{"key":"15_CR65","doi-asserted-by":"crossref","unstructured":"Wei, Q.A., et al.: LEGO-Net: learning regular rearrangements of objects in rooms. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01825"},{"key":"15_CR66","first-page":"3231","volume":"25","author":"T Weiss","year":"2018","unstructured":"Weiss, T., et al.: Fast and scalable position-based layout synthesis. IEEE TVCG 25, 3231\u20133243 (2018)","journal-title":"IEEE TVCG"},{"key":"15_CR67","unstructured":"Xu, K., Wu, L., Wang, Z., Feng, Y., Witbrock, M., Sheinin, V.: Graph2seq: graph to sequence learning with attention-based neural networks. arXiv preprint arXiv:1804.00823 (2018)"},{"key":"15_CR68","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 TOG 30 (2011)","DOI":"10.1145\/2010324.1964981"},{"key":"15_CR69","first-page":"1138","volume":"22","author":"LF Yu","year":"2015","unstructured":"Yu, L.F., Yeung, S.K., Terzopoulos, D.: The ClutterPalette: an interactive tool for detailing indoor scenes. IEEE TVCG 22, 1138\u20131148 (2015)","journal-title":"IEEE TVCG"},{"key":"15_CR70","unstructured":"Zaheer, M., Kottur, S., Ravanbhakhsh, S., P\u00f3czos, B., Salakhutdinov, R., Smola, A.J.: Deep sets. In: NeurIPS (2017)"},{"key":"15_CR71","doi-asserted-by":"crossref","unstructured":"Zellers, R., Yatskar, M., Thomson, S., Choi, Y.: Neural motifs: scene graph parsing with global context. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00611"},{"key":"15_CR72","unstructured":"Zhai, G., \u00d6rnek, E.P., Wu, S.C., Di, Y., Tombari, F., Navab, N., Busam, B.: CommonScenes: generating commonsense 3D indoor scenes with scene graphs. arXiv preprint arXiv:2305.16283 (2023)"},{"key":"15_CR73","first-page":"1","volume":"35","author":"X Zhao","year":"2016","unstructured":"Zhao, X., Hu, R., Guerrero, P., Mitra, N., Komura, T.: Relationship templates for creating scene variations. ACM TOG 35, 1\u201313 (2016)","journal-title":"ACM TOG"},{"key":"15_CR74","unstructured":"Zhao, Y., et al.: Luminous: indoor scene generation for embodied ai challenges. In: NeurIPSW (2021)"},{"key":"15_CR75","doi-asserted-by":"crossref","unstructured":"Zhou, Y., While, Z., Kalogerakis, E.: SceneGraphNet: neural message passing for 3D indoor scene augmentation. In: CVPR (2019)","DOI":"10.1109\/ICCV.2019.00748"}],"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\/978-3-031-72698-9_15","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,25]],"date-time":"2024-10-25T00:50:15Z","timestamp":1729817415000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72698-9_15"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,26]]},"ISBN":["9783031726972","9783031726989"],"references-count":75,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72698-9_15","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"}}]}}