{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,6]],"date-time":"2026-07-06T14:27:09Z","timestamp":1783348029344,"version":"3.54.6"},"reference-count":36,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2024,7,15]],"date-time":"2024-07-15T00:00:00Z","timestamp":1721001600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,7,15]],"date-time":"2024-07-15T00:00:00Z","timestamp":1721001600000},"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":["Vis Comput"],"published-print":{"date-parts":[[2025,3]]},"DOI":"10.1007\/s00371-024-03573-2","type":"journal-article","created":{"date-parts":[[2024,7,15]],"date-time":"2024-07-15T05:01:22Z","timestamp":1721019682000},"page":"2875-2889","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["3D-Scene-Former: 3D scene generation from a single RGB image using Transformers"],"prefix":"10.1007","volume":"41","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1760-6573","authenticated-orcid":false,"given":"Jit","family":"Chatterjee","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5656-6607","authenticated-orcid":false,"given":"Maria","family":"Torres\u00a0Vega","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,7,15]]},"reference":[{"key":"3573_CR1","unstructured":"Dahnert, M., Hou, J., Nie\u00dfner, M., Dai, A.: Panoptic 3D scene reconstruction from a single RGB image. In: Advances in Neural Information Processing Systems (2021)"},{"key":"3573_CR2","doi-asserted-by":"publisher","unstructured":"Chatterjee, J., Torres\u00a0Vega, M.: Human-centered and ai-driven generation of 6-dof extended reality. In: Proceedings of the 2023 ACM International Conference on Interactive Media Experiences, pp. 398\u2013401. Association for Computing Machinery, New York, NY, USA (2023). https:\/\/doi.org\/10.1145\/3573381.3597232","DOI":"10.1145\/3573381.3597232"},{"key":"3573_CR3","doi-asserted-by":"publisher","unstructured":"Lepetit, V., Moreno-Noguer, F., Fua, P.: EPNP: an accurate o(n) solution to the PNP problem. Int. J. Comput. Vis. 81 (2009). https:\/\/doi.org\/10.1007\/s11263-008-0152-6","DOI":"10.1007\/s11263-008-0152-6"},{"key":"3573_CR4","doi-asserted-by":"publisher","first-page":"381","DOI":"10.1145\/358669.358692","volume":"24","author":"MA Fischler","year":"1981","unstructured":"Fischler, M.A., Bolles, R.C.: Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography. Commun. ACM 24, 381\u2013395 (1981). https:\/\/doi.org\/10.1145\/358669.358692","journal-title":"Commun. ACM"},{"key":"3573_CR5","doi-asserted-by":"publisher","first-page":"231","DOI":"10.1007\/s11263-005-3674-1","volume":"66","author":"F Rothganger","year":"2006","unstructured":"Rothganger, F., Lazebnik, S., Schmid, C., Ponce, J.: 3D object modeling and recognition using local affine-invariant image descriptors and multi-view spatial constraints. Int. J. Comput. Vis. 66, 231\u2013259 (2006). https:\/\/doi.org\/10.1007\/s11263-005-3674-1","journal-title":"Int. J. Comput. Vis."},{"key":"3573_CR6","doi-asserted-by":"publisher","unstructured":"Huang, S., Qi, S., Zhu, Y., Xiao, Y., Xu, Y., Zhu, S.-C.: Holistic 3D scene parsing and reconstruction from a single RGB image. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 187\u2013203 (2018). https:\/\/doi.org\/10.1007\/978-3-030-01234-2_12","DOI":"10.1007\/978-3-030-01234-2_12"},{"key":"3573_CR7","doi-asserted-by":"publisher","unstructured":"Nie, Y., Han, X., Guo, S., Zheng, Y., Chang, J., Zhang, J.J.: Total3dunderstanding: joint layout, object pose and mesh reconstruction for indoor scenes from a single image. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 52\u201361 (2020). https:\/\/doi.org\/10.1109\/CVPR42600.2020.00013","DOI":"10.1109\/CVPR42600.2020.00013"},{"key":"3573_CR8","doi-asserted-by":"publisher","unstructured":"Zhang, C., Cui, Z., Zhang, Y., Zeng, B., Pollefeys, M., Liu, S.: Holistic 3D scene understanding from a single image with implicit representation. In: 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 8829\u20138838 (2021). https:\/\/doi.org\/10.1109\/CVPR46437.2021.00872","DOI":"10.1109\/CVPR46437.2021.00872"},{"key":"3573_CR9","unstructured":"Huang, S., Qi, S., Xiao, Y., Zhu, Y., Wu, Y.N., Zhu, S.-C.: Cooperative holistic scene understanding: unifying 3D object, layout, and camera pose estimation. In: Advances in Neural Information Processing Systems, pp. 206\u2013217 (2018). https:\/\/dl.acm.org\/doi\/10.5555\/3326943.3326963"},{"key":"3573_CR10","doi-asserted-by":"publisher","unstructured":"Yang, J., Lu, J., Lee, S., Batra, D., Parikh, D.: Graph r-CNN for scene graph generation. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 670\u2013685 (2018). https:\/\/doi.org\/10.1007\/978-3-030-01246-5_41","DOI":"10.1007\/978-3-030-01246-5_41"},{"key":"3573_CR11","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, L., Polosukhin, I.: Attention is all you need. In: Proceedings of the 31st International Conference on Neural Information Processing Systems, pp. 6000\u20136010 (2017). https:\/\/dl.acm.org\/doi\/10.5555\/3295222.3295349"},{"key":"3573_CR12","doi-asserted-by":"publisher","unstructured":"Genova, K., Cole, F., Sud, A., Sarna, A., Funkhouser, T.: Local deep implicit functions for 3D shape. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4856\u20134865 (2020).https:\/\/doi.org\/10.1109\/CVPR42600.2020.00491","DOI":"10.1109\/CVPR42600.2020.00491"},{"key":"3573_CR13","doi-asserted-by":"publisher","unstructured":"Tombari, F., Di\u00a0Stefano, L.: Object recognition in 3D scenes with occlusions and clutter by Hough voting. In: 2010 Fourth Pacific-Rim Symposium on Image and Video Technology, pp. 349\u2013355 (2010). https:\/\/doi.org\/10.1109\/PSIVT.2010.65","DOI":"10.1109\/PSIVT.2010.65"},{"issue":"3","key":"3573_CR14","doi-asserted-by":"publisher","first-page":"80","DOI":"10.1109\/MRA.2012.2206675","volume":"19","author":"A Aldoma","year":"2012","unstructured":"Aldoma, A., Marton, Z.-C., Tombari, F., Wohlkinger, W., Potthast, C., Zeisl, B., Rusu, R.B., Gedikli, S., Vincze, M.: Tutorial: point cloud library: three-dimensional object recognition and 6 DOF pose estimation. IEEE Robot. Autom. Mag. 19(3), 80\u201391 (2012). https:\/\/doi.org\/10.1109\/MRA.2012.2206675","journal-title":"IEEE Robot. Autom. Mag."},{"key":"3573_CR15","doi-asserted-by":"publisher","unstructured":"Karpathy, A., Miller, S., Fei-Fei, L.: Object discovery in 3D scenes via shape analysis. In: 2013 IEEE International Conference on Robotics and Automation, pp. 2088\u20132095 (2013). https:\/\/doi.org\/10.1109\/ICRA.2013.6630857","DOI":"10.1109\/ICRA.2013.6630857"},{"key":"3573_CR16","doi-asserted-by":"publisher","unstructured":"Song, S., Xiao, J.: Sliding shapes for 3D object detection in depth images. In: Computer Vision\u2014ECCV 2014, pp. 634\u2013651 (2014). https:\/\/doi.org\/10.1007\/978-3-319-10599-4_41","DOI":"10.1007\/978-3-319-10599-4_41"},{"key":"3573_CR17","doi-asserted-by":"publisher","unstructured":"Song, S., Xiao, J.: Deep sliding shapes for a modal 3D object detection in RGB-D images. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 808\u2013816 (2016).https:\/\/doi.org\/10.1109\/CVPR.2016.94","DOI":"10.1109\/CVPR.2016.94"},{"key":"3573_CR18","doi-asserted-by":"publisher","unstructured":"Qi, C.R., Liu, W., Wu, C., Su, H., Guibas, L.J.: Frustum pointnets for 3D object detection from RGB-d data. In: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 918\u2013927 (2018). https:\/\/doi.org\/10.1109\/CVPR.2018.00102","DOI":"10.1109\/CVPR.2018.00102"},{"key":"3573_CR19","doi-asserted-by":"publisher","unstructured":"Mousavian, A., Anguelov, D., Flynn, J., Kosecka, J.: 3D bounding box estimation using deep learning and geometry. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5632\u20135640 (2017). https:\/\/doi.org\/10.1109\/CVPR.2017.597","DOI":"10.1109\/CVPR.2017.597"},{"key":"3573_CR20","unstructured":"Huang, S., Chen, Y., Yuan, T., Qi, S., Zhu, Y., Zhu, S.-C.: Perspectivenet: 3D object detection from a single RGB image via perspective points. In: Proceedings of the 33rd International Conference on Neural Information Processing Systems (2019). https:\/\/dl.acm.org\/doi\/10.5555\/3454287.3455086"},{"key":"3573_CR21","doi-asserted-by":"publisher","unstructured":"G\u00fcmeli, C., Dai, A., Nie\u00dfner, M.: ROCA: robust cad model retrieval and alignment from a single image. In: 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4012\u20134021 (2022). https:\/\/doi.org\/10.1109\/CVPR52688.2022.00399","DOI":"10.1109\/CVPR52688.2022.00399"},{"key":"3573_CR22","unstructured":"Ramp\u00e1\u0161ek, L., Galkin, M., Dwivedi, V.P., Luu, A.T., Wolf, G., Beaini, D.: Recipe for a general, powerful, scalable graph transformer. In: Advances in Neural Information Processing Systems, vol. 35, pp. 14501\u201314515 (2022). https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2022\/file\/5d4834a159f1547b267a05a4e2b7cf5e-Paper-Conference.pdf"},{"key":"3573_CR23","doi-asserted-by":"publisher","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. In: Computer Vision\u2014ECCV 2020, pp. 213\u2013229 (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_13","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"3573_CR24","doi-asserted-by":"publisher","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770\u2013778 (2016). https:\/\/doi.org\/10.1109\/CVPR.2016.90","DOI":"10.1109\/CVPR.2016.90"},{"key":"3573_CR25","doi-asserted-by":"publisher","unstructured":"Lin, T.-Y., Doll\u00e1r, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 936\u2013944 (2017). https:\/\/doi.org\/10.1109\/CVPR.2017.106","DOI":"10.1109\/CVPR.2017.106"},{"key":"3573_CR26","doi-asserted-by":"publisher","unstructured":"Hu, J., Ozay, M., Zhang, Y., Okatani, T.: Revisiting single image depth estimation: toward higher resolution maps with accurate object boundaries. In: 2019 IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 1043\u20131051 (2019). https:\/\/doi.org\/10.1109\/WACV.2019.00116","DOI":"10.1109\/WACV.2019.00116"},{"key":"3573_CR27","doi-asserted-by":"publisher","unstructured":"Shi, W., Caballero, J., Husz\u00e1r, F., Totz, J., Aitken, A.P., Bishop, R., Rueckert, D., Wang, Z.: Real-time single image and video super-resolution using an efficient sub-pixel convolutional neural network. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1874\u20131883 (2016). https:\/\/doi.org\/10.1109\/CVPR.2016.207","DOI":"10.1109\/CVPR.2016.207"},{"key":"3573_CR28","doi-asserted-by":"publisher","unstructured":"Laina, I., Rupprecht, C., Belagiannis, V., Tombari, F., Navab, N.: Deeper depth prediction with fully convolutional residual networks. In: 2016 Fourth International Conference on 3D Vision (3DV), pp. 239\u2013248. IEEE (2016). https:\/\/doi.org\/10.1109\/3DV.2016.32","DOI":"10.1109\/3DV.2016.32"},{"issue":"6","key":"3573_CR29","doi-asserted-by":"publisher","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","volume":"39","author":"S Ren","year":"2017","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster r-CNN: towards real-time object detection with region proposal networks. IEEE Trans. Pattern Anal. Mach. Intell. 39(6), 1137\u20131149 (2017). https:\/\/doi.org\/10.1109\/TPAMI.2016.2577031","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"3573_CR30","doi-asserted-by":"publisher","unstructured":"Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S.E., Fu, C.-Y., Berg, A.C.: SSD: single shot multibox detector. In: Computer Vision ECCV 2016. Lecture Notes in Computer Science, vol. 9905, pp. 21\u201337 (2016). https:\/\/doi.org\/10.1007\/978-3-319-46448-0_2","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"3573_CR31","doi-asserted-by":"publisher","unstructured":"Song, S., Lichtenberg, S.P., Xiao, J.: Sun RGB-D: a RGB-D scene understanding benchmark suite. In: 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 567\u2013576 (2015). https:\/\/doi.org\/10.1109\/CVPR.2015.7298655","DOI":"10.1109\/CVPR.2015.7298655"},{"key":"3573_CR32","doi-asserted-by":"publisher","unstructured":"Sun, X., Wu, J., Zhang, X., Zhang, Z., Zhang, C., Xue, T., Tenenbaum, J.B., Freeman, W.T.: Pix3d: dataset and methods for single-image 3D shape modeling. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2018). https:\/\/doi.org\/10.1109\/CVPR.2018.00314","DOI":"10.1109\/CVPR.2018.00314"},{"key":"3573_CR33","doi-asserted-by":"publisher","unstructured":"Silberman, N., Hoiem, D., Kohli, P., Fergus, R.: Indoor segmentation and support inference from RGBD images. In: European Conference on Computer Vision (2012). https:\/\/doi.org\/10.1007\/978-3-642-33715-4_54","DOI":"10.1007\/978-3-642-33715-4_54"},{"key":"3573_CR34","doi-asserted-by":"publisher","unstructured":"Gkioxari, G., Johnson, J., Malik, J.: Mesh R-CNN. In: 2019 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 9784\u20139794 (2019). https:\/\/doi.org\/10.1109\/ICCV.2019.00988","DOI":"10.1109\/ICCV.2019.00988"},{"key":"3573_CR35","unstructured":"Wu, Y., Kirillov, A., Massa, F., Lo, W.-Y., Girshick, R.: Detectron2. https:\/\/github.com\/facebookresearch\/detectron2 (2019)"},{"key":"3573_CR36","doi-asserted-by":"publisher","unstructured":"Liu, Z., Zhang, Z., Cao, Y., Hu, H., Tong, X.: Group-free 3D object detection via transformers. In: 2021 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 2929\u20132938 (2021). https:\/\/doi.org\/10.1109\/ICCV48922.2021.00294","DOI":"10.1109\/ICCV48922.2021.00294"}],"container-title":["The Visual Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-024-03573-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00371-024-03573-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-024-03573-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,3]],"date-time":"2025-03-03T11:31:32Z","timestamp":1741001492000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00371-024-03573-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,15]]},"references-count":36,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2025,3]]}},"alternative-id":["3573"],"URL":"https:\/\/doi.org\/10.1007\/s00371-024-03573-2","relation":{},"ISSN":["0178-2789","1432-2315"],"issn-type":[{"value":"0178-2789","type":"print"},{"value":"1432-2315","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,7,15]]},"assertion":[{"value":"6 July 2024","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 July 2024","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}]}}