{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T21:30:24Z","timestamp":1778103024916,"version":"3.51.4"},"publisher-location":"Cham","reference-count":65,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031731945","type":"print"},{"value":"9783031731952","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T00:00:00Z","timestamp":1732665600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T00:00:00Z","timestamp":1732665600000},"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\/978-3-031-73195-2_2","type":"book-chapter","created":{"date-parts":[[2024,11,26]],"date-time":"2024-11-26T09:36:24Z","timestamp":1732613784000},"page":"18-35","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["InterFusion: Text-Driven Generation of\u00a03D Human-Object Interaction"],"prefix":"10.1007","author":[{"given":"Sisi","family":"Dai","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenhao","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haowen","family":"Sun","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haibin","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chongyang","family":"Ma","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hui","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kai","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruizhen","family":"Hu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,11,27]]},"reference":[{"key":"2_CR1","doi-asserted-by":"crossref","unstructured":"Bhatnagar, B.L., Xie, X., Petrov, I.A., Sminchisescu, C., Theobalt, C., Pons-Moll, G.: Behave: dataset and method for tracking human object interactions. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15935\u201315946 (2022)","DOI":"10.1109\/CVPR52688.2022.01547"},{"key":"2_CR2","unstructured":"Chang, A.X., et\u00a0al.: Shapenet: an information-rich 3D model repository. arXiv preprint arXiv:1512.03012 (2015)"},{"key":"2_CR3","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":"2_CR4","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. arXiv preprint arXiv:2303.13450 (2023)","DOI":"10.1109\/ICCVW60793.2023.00314"},{"key":"2_CR5","unstructured":"Deepfloyd IF (2023). https:\/\/github.com\/deep-floyd\/IF"},{"key":"2_CR6","doi-asserted-by":"crossref","unstructured":"Diller, C., Dai, A.: CG-HOI: contact-guided 3D human-object interaction generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 19888\u201319901 (2024)","DOI":"10.1109\/CVPR52733.2024.01880"},{"key":"2_CR7","unstructured":"Fan, Z., et al.: Articulated objects in free-form hand interaction. arXiv preprint arXiv:2204.13662 (2022)"},{"key":"2_CR8","doi-asserted-by":"crossref","unstructured":"Feng, Y., Choutas, V., Bolkart, T., Tzionas, D., Black, M.J.: Collaborative regression of expressive bodies using moderation. In: 2021 International Conference on 3D Vision (3DV), pp. 792\u2013804. IEEE (2021)","DOI":"10.1109\/3DV53792.2021.00088"},{"key":"2_CR9","doi-asserted-by":"crossref","unstructured":"Guo, C., et al.: Generating diverse and natural 3D human motions from text. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5152\u20135161 (2022)","DOI":"10.1109\/CVPR52688.2022.00509"},{"key":"2_CR10","unstructured":"Guo, M., Fathi, A., Wu, J., Funkhouser, T.: Object-centric neural scene rendering. arXiv preprint arXiv:2012.08503 (2020)"},{"key":"2_CR11","unstructured":"Guo, Y.C., et al.: threestudio: a unified framework for 3D content generation (2023). https:\/\/github.com\/threestudio-project\/threestudio"},{"key":"2_CR12","doi-asserted-by":"crossref","unstructured":"Hassan, M., Choutas, V., Tzionas, D., Black, M.J.: Resolving 3D human pose ambiguities with 3D scene constraints. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 2282\u20132292 (2019)","DOI":"10.1109\/ICCV.2019.00237"},{"key":"2_CR13","doi-asserted-by":"crossref","unstructured":"Hassan, M., Ghosh, P., Tesch, J., Tzionas, D., Black, M.J.: Populating 3D scenes by learning human-scene interaction. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14708\u201314718 (2021)","DOI":"10.1109\/CVPR46437.2021.01447"},{"key":"2_CR14","doi-asserted-by":"crossref","unstructured":"Hong, F., Zhang, M., Pan, L., Cai, Z., Yang, L., Liu, Z.: Avatarclip: zero-shot text-driven generation and animation of 3D avatars. arXiv preprint arXiv:2205.08535 (2022)","DOI":"10.1145\/3528223.3530094"},{"key":"2_CR15","doi-asserted-by":"crossref","unstructured":"Ionescu, C., Papava, D., Olaru, V., Sminchisescu, C.: Human3.6m: large scale datasets and predictive methods for 3D human sensing in natural environments. IEEE Trans. Pattern Anal. Mach. Intell. 36(7), 1325\u20131339 (2013)","DOI":"10.1109\/TPAMI.2013.248"},{"key":"2_CR16","doi-asserted-by":"crossref","unstructured":"Jahan, T., Guan, Y., Van\u00a0Kaick, O.: Semantics-guided latent space exploration for shape generation. In: Computer Graphics Forum, vol.\u00a040, pp. 115\u2013126. Wiley Online Library (2021)","DOI":"10.1111\/cgf.142619"},{"key":"2_CR17","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. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 867\u2013876 (2022)","DOI":"10.1109\/CVPR52688.2022.00094"},{"key":"2_CR18","doi-asserted-by":"crossref","unstructured":"Kim, V.G., Chaudhuri, S., Guibas, L., Funkhouser, T.: Shape2Pose: human-centric shape analysis. ACM Trans. Graph. (Proc. SIGGRAPH) (2014)","DOI":"10.1145\/2601097.2601117"},{"key":"2_CR19","unstructured":"Kingma, D.P., Welling, M.: Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114 (2013)"},{"key":"2_CR20","unstructured":"Lee, H.H., Chang, A.X.: Understanding pure clip guidance for voxel grid nerf models. arXiv preprint arXiv:2209.15172 (2022)"},{"key":"2_CR21","doi-asserted-by":"crossref","unstructured":"Lin, C.H., et al.: Magic3d: high-resolution text-to-3D content creation. arXiv preprint arXiv:2211.10440 (2022)","DOI":"10.1109\/CVPR52729.2023.00037"},{"key":"2_CR22","unstructured":"Lin, Y., et al.: Componerf: text-guided multi-object compositional nerf with editable 3D scene layout. arXiv preprint arXiv:2303.13843 (2023)"},{"key":"2_CR23","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"423","DOI":"10.1007\/978-3-031-19790-1_26","volume-title":"European Conference on Computer Vision","author":"N Liu","year":"2022","unstructured":"Liu, N., Li, S., Du, Y., Torralba, A., Tenenbaum, J.B.: Compositional visual generation with composable diffusion models. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13677, pp. 423\u2013439. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19790-1_26"},{"key":"2_CR24","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":"6","key":"2_CR25","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/2816795.2818013","volume":"34","author":"M Loper","year":"2015","unstructured":"Loper, M., Mahmood, N., Romero, J., Pons-Moll, G., Black, M.J.: SMPL: a skinned multi-person linear model. ACM Trans. Graph. (TOG) 34(6), 1\u201316 (2015)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"2_CR26","doi-asserted-by":"crossref","unstructured":"Mahmood, N., Ghorbani, N., Troje, N.F., Pons-Moll, G., Black, M.J.: Amass: archive of motion capture as surface shapes. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 5442\u20135451 (2019)","DOI":"10.1109\/ICCV.2019.00554"},{"key":"2_CR27","doi-asserted-by":"crossref","unstructured":"Metzer, G., Richardson, E., Patashnik, O., Giryes, R., Cohen-Or, D.: Latent-nerf for shape-guided generation of 3D shapes and textures. arXiv preprint arXiv:2211.07600 (2022)","DOI":"10.1109\/CVPR52729.2023.01218"},{"key":"2_CR28","doi-asserted-by":"crossref","unstructured":"Michel, O., Bar-On, R., Liu, R., Benaim, S., Hanocka, R.: Text2mesh: text-driven neural stylization for meshes. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13492\u201313502 (2022)","DOI":"10.1109\/CVPR52688.2022.01313"},{"key":"2_CR29","doi-asserted-by":"crossref","unstructured":"Mihajlovic, M., Saito, S., Bansal, A., Zollhoefer, M., Tang, S.: COAP: compositional articulated occupancy of people. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13201\u201313210 (2022)","DOI":"10.1109\/CVPR52688.2022.01285"},{"issue":"1","key":"2_CR30","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1145\/3503250","volume":"65","author":"B Mildenhall","year":"2021","unstructured":"Mildenhall, B., Srinivasan, P.P., Tancik, M., Barron, J.T., Ramamoorthi, R., Ng, R.: Nerf: representing scenes as neural radiance fields for view synthesis. Commun. ACM 65(1), 99\u2013106 (2021)","journal-title":"Commun. ACM"},{"key":"2_CR31","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1007\/978-3-031-20062-5_2","volume-title":"European Conference on Computer Vision","author":"A Mirzaei","year":"2022","unstructured":"Mirzaei, A., Kant, Y., Kelly, J., Gilitschenski, I.: LaTeRF: label and text driven object radiance fields. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13663, pp. 20\u201336. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20062-5_2"},{"key":"2_CR32","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"},{"issue":"4","key":"2_CR33","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3528223.3530127","volume":"41","author":"T M\u00fcller","year":"2022","unstructured":"M\u00fcller, T., Evans, A., Schied, C., Keller, A.: Instant neural graphics primitives with a multiresolution hash encoding. ACM Trans. Graph. (ToG) 41(4), 1\u201315 (2022)","journal-title":"ACM Trans. Graph. (ToG)"},{"key":"2_CR34","first-page":"6767","volume":"33","author":"TH Nguyen-Phuoc","year":"2020","unstructured":"Nguyen-Phuoc, T.H., Richardt, C., Mai, L., Yang, Y., Mitra, N.: Blockgan: learning 3D object-aware scene representations from unlabelled images. Adv. Neural. Inf. Process. Syst. 33, 6767\u20136778 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"2_CR35","doi-asserted-by":"crossref","unstructured":"Niemeyer, M., Geiger, A.: Giraffe: representing scenes as compositional generative neural feature fields. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11453\u201311464 (2021)","DOI":"10.1109\/CVPR46437.2021.01129"},{"key":"2_CR36","doi-asserted-by":"crossref","unstructured":"Ost, J., Mannan, F., Thuerey, N., Knodt, J., Heide, F.: Neural scene graphs for dynamic scenes. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2856\u20132865 (2021)","DOI":"10.1109\/CVPR46437.2021.00288"},{"key":"2_CR37","doi-asserted-by":"crossref","unstructured":"Pavlakos, G., et al.: Expressive body capture: 3D hands, face, and body from a single image. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10975\u201310985 (2019)","DOI":"10.1109\/CVPR.2019.01123"},{"key":"2_CR38","unstructured":"Peng, X., Xie, Y., Wu, Z., Jampani, V., Sun, D., Jiang, H.: Hoi-diff: text-driven synthesis of 3D human-object interactions using diffusion models. arXiv preprint arXiv:2312.06553 (2023)"},{"key":"2_CR39","doi-asserted-by":"crossref","unstructured":"Po, R., Wetzstein, G.: Compositional 3D scene generation using locally conditioned diffusion. arXiv preprint arXiv:2303.12218 (2023)","DOI":"10.1109\/3DV62453.2024.00026"},{"key":"2_CR40","unstructured":"Poole, B., Jain, A., Barron, J.T., Mildenhall, B.: Dreamfusion: text-to-3D using 2D diffusion. arXiv preprint arXiv:2209.14988 (2022)"},{"key":"2_CR41","unstructured":"Puig, X., et\u00a0al.: Habitat 3.0: a co-habitat for humans, avatars and robots. arXiv preprint arXiv:2310.13724 (2023)"},{"key":"2_CR42","doi-asserted-by":"crossref","unstructured":"Punnakkal, A.R., Chandrasekaran, A., Athanasiou, N., Quiros-Ramirez, A., Black, M.J.: Babel: bodies, action and behavior with english labels. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 722\u2013731 (2021)","DOI":"10.1109\/CVPR46437.2021.00078"},{"key":"2_CR43","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":"2_CR44","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\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10684\u201310695 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"2_CR45","unstructured":"Romero, J., Tzionas, D., Black, M.J.: Embodied hands: modeling and capturing hands and bodies together. arXiv preprint arXiv:2201.02610 (2022)"},{"key":"2_CR46","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. Adv. Neural. Inf. Process. Syst. 35, 36479\u201336494 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"issue":"4","key":"2_CR47","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/2897824.2925867","volume":"35","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 Trans. Graph. (TOG) 35(4), 1\u201312 (2016)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"2_CR48","doi-asserted-by":"crossref","unstructured":"Sella, E., Fiebelman, G., Hedman, P., Averbuch-Elor, H.: Vox-e: text-guided voxel editing of 3D objects. arXiv preprint arXiv:2303.12048 (2023)","DOI":"10.1109\/ICCV51070.2023.00046"},{"issue":"4","key":"2_CR49","doi-asserted-by":"publisher","first-page":"525","DOI":"10.1177\/0018720816644364","volume":"58","author":"TB Sheridan","year":"2016","unstructured":"Sheridan, T.B.: Human-robot interaction: status and challenges. Hum. Factors 58(4), 525\u2013532 (2016)","journal-title":"Hum. Factors"},{"key":"2_CR50","unstructured":"Shi, Y., Wang, P., Ye, J., Long, M., Li, K., Yang, X.: Mvdream: multi-view diffusion for 3D generation. arXiv preprint arXiv:2308.16512 (2023)"},{"key":"2_CR51","unstructured":"Sohn, K., Lee, H., Yan, X.: Learning structured output representation using deep conditional generative models. In: Advances in Neural Information Processing Systems, vol. 28 (2015)"},{"key":"2_CR52","unstructured":"Song, Y., Kong, C., Lee, S., Kwak, N., Lee, J.: Towards efficient neural scene graphs by learning consistency fields. arXiv preprint arXiv:2210.04127 (2022)"},{"key":"2_CR53","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"581","DOI":"10.1007\/978-3-030-58548-8_34","volume-title":"Computer Vision \u2013 ECCV 2020","author":"O Taheri","year":"2020","unstructured":"Taheri, O., Ghorbani, N., Black, M.J., Tzionas, D.: GRAB: a dataset of whole-body human grasping of objects. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12349, pp. 581\u2013600. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58548-8_34"},{"key":"2_CR54","doi-asserted-by":"crossref","unstructured":"Tsalicoglou, C., Manhardt, F., Tonioni, A., Niemeyer, M., Tombari, F.: Textmesh: generation of realistic 3D meshes from text prompts. arXiv preprint arXiv:2304.12439 (2023)","DOI":"10.1109\/3DV62453.2024.00154"},{"key":"2_CR55","doi-asserted-by":"crossref","unstructured":"Von\u00a0Marcard, T., Henschel, R., Black, M.J., Rosenhahn, B., Pons-Moll, G.: Recovering accurate 3D human pose in the wild using IMUs and a moving camera. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 601\u2013617 (2018)","DOI":"10.1007\/978-3-030-01249-6_37"},{"key":"2_CR56","doi-asserted-by":"crossref","unstructured":"Wang, H., Du, X., Li, J., Yeh, R.A., Shakhnarovich, G.: Score jacobian chaining: lifting pretrained 2D diffusion models for 3D generation. arXiv preprint arXiv:2212.00774 (2022)","DOI":"10.1109\/CVPR52729.2023.01214"},{"key":"2_CR57","unstructured":"Wang, Z., et al.: Prolificdreamer: high-fidelity and diverse text-to-3D generation with variational score distillation. In: Advances in Neural Information Processing Systems, vol. 36 (2024)"},{"key":"2_CR58","unstructured":"Wu, Q., Shi, Y., Huang, X., Yu, J., Xu, L., Wang, J.: Thor: text to human-object interaction diffusion via relation intervention. arXiv preprint arXiv:2403.11208 (2024)"},{"key":"2_CR59","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"197","DOI":"10.1007\/978-3-031-19812-0_12","volume-title":"European Conference on Computer Vision","author":"Q Wu","year":"2022","unstructured":"Wu, Q., Liu, X., Chen, Y., Li, K., Zheng, C., Cai, J., Zheng, J.: Object-compositional neural implicit surfaces. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13687, pp. 197\u2013213. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19812-0_12"},{"key":"2_CR60","doi-asserted-by":"crossref","unstructured":"Xu, Y., et\u00a0al.: Discoscene: spatially disentangled generative radiance fields for controllable 3D-aware scene synthesis. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4402\u20134412 (2023)","DOI":"10.1109\/CVPR52729.2023.00428"},{"key":"2_CR61","doi-asserted-by":"crossref","unstructured":"Yang, B., et al.: Learning object-compositional neural radiance field for editable scene rendering. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 13779\u201313788 (2021)","DOI":"10.1109\/ICCV48922.2021.01352"},{"key":"2_CR62","doi-asserted-by":"crossref","unstructured":"Zhang, S., Zhang, Y., Ma, Q., Black, M.J., Tang, S.: Place: proximity learning of articulation and contact in 3D environments. In: 2020 International Conference on 3D Vision (3DV), pp. 642\u2013651. IEEE (2020)","DOI":"10.1109\/3DV50981.2020.00074"},{"key":"2_CR63","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Hassan, M., Neumann, H., Black, M.J., Tang, S.: Generating 3D people in scenes without people. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6194\u20136204 (2020)","DOI":"10.1109\/CVPR42600.2020.00623"},{"key":"2_CR64","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"311","DOI":"10.1007\/978-3-031-20068-7_18","volume-title":"European Conference on Computer Vision","author":"K Zhao","year":"2022","unstructured":"Zhao, K., Wang, S., Zhang, Y., Beeler, T., Tang, S.: Compositional human-scene interaction synthesis with semantic control. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13666, pp. 311\u2013327. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20068-7_18"},{"key":"2_CR65","doi-asserted-by":"crossref","unstructured":"Zhi, S., Laidlow, T., Leutenegger, S., Davison, A.J.: In-place scene labelling and understanding with implicit scene representation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 15838\u201315847 (2021)","DOI":"10.1109\/ICCV48922.2021.01554"}],"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\/978-3-031-73195-2_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,26]],"date-time":"2024-11-26T10:04:09Z","timestamp":1732615449000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73195-2_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,27]]},"ISBN":["9783031731945","9783031731952"],"references-count":65,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73195-2_2","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,27]]},"assertion":[{"value":"27 November 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"}}]}}