{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,31]],"date-time":"2026-10-31T19:59:59Z","timestamp":1793476799875,"version":"4.5.0"},"publisher-location":"Cham","reference-count":44,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030012489","type":"print"},{"value":"9783030012496","type":"electronic"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018]]},"DOI":"10.1007\/978-3-030-01249-6_28","type":"book-chapter","created":{"date-parts":[[2018,10,5]],"date-time":"2018-10-05T11:35:46Z","timestamp":1538739346000},"page":"458-474","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":256,"title":["3DMV: Joint 3D-Multi-view Prediction for 3D Semantic Scene Segmentation"],"prefix":"10.1007","author":[{"given":"Angela","family":"Dai","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Matthias","family":"Nie\u00dfner","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2018,10,6]]},"reference":[{"key":"28_CR1","doi-asserted-by":"crossref","unstructured":"Chang, A., et al.: Matterport3D: learning from RGB-D data in indoor environments. In: International Conference on 3D Vision (3DV) (2017)","DOI":"10.1109\/3DV.2017.00081"},{"key":"28_CR2","unstructured":"Chang, A.X., et al.: ShapeNet: an information-rich 3D model repository. Technical report, Stanford University \u2013 Princeton University \u2013 Toyota Technological Institute at Chicago. arXiv:1512.03012 [cs.GR] (2015)"},{"key":"28_CR3","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"628","DOI":"10.1007\/978-3-319-46484-8_38","volume-title":"Computer Vision \u2013 ECCV 2016","author":"CB Choy","year":"2016","unstructured":"Choy, C.B., Xu, D., Gwak, J.Y., Chen, K., Savarese, S.: 3D-R2N2: a unified approach for single and multi-view 3D object reconstruction. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9912, pp. 628\u2013644. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46484-8_38"},{"key":"28_CR4","doi-asserted-by":"crossref","unstructured":"Curless, B., Levoy, M.: A volumetric method for building complex models from range images. In: Proceedings of the 23rd Annual Conference on Computer Graphics and Interactive Techniques, pp. 303\u2013312. ACM (1996)","DOI":"10.1145\/237170.237269"},{"key":"28_CR5","doi-asserted-by":"crossref","unstructured":"Dai, A., Chang, A.X., Savva, M., Halber, M., Funkhouser, T., Nie\u00dfner, M.: ScanNet: richly-annotated 3D reconstructions of indoor scenes. In: Proceedings of Computer Vision and Pattern Recognition (CVPR). IEEE (2017)","DOI":"10.1109\/CVPR.2017.261"},{"issue":"3","key":"28_CR6","first-page":"24","volume":"36","author":"A Dai","year":"2017","unstructured":"Dai, A., Nie\u00dfner, M., Zollh\u00f6fer, M., Izadi, S., Theobalt, C.: BundleFusion: real-time globally consistent 3D reconstruction using on-the-fly surface reintegration. ACM Trans. Gr. (TOG) 36(3), 24 (2017)","journal-title":"ACM Trans. Gr. (TOG)"},{"key":"28_CR7","doi-asserted-by":"crossref","unstructured":"Dai, A., Qi, C.R., Nie\u00dfner, M.: Shape completion using 3D-encoder-predictor CNNs and shape synthesis. In: Proceedings of Computer Vision and Pattern Recognition (CVPR). IEEE (2017)","DOI":"10.1109\/CVPR.2017.693"},{"key":"28_CR8","doi-asserted-by":"crossref","unstructured":"Dai, A., Ritchie, D., Bokeloh, M., Reed, S., Sturm, J., Nie\u00dfner, M.: ScanComplete: large-scale scene completion and semantic segmentation for 3D scans. arXiv preprint arXiv:1712.10215 (2018)","DOI":"10.1109\/CVPR.2018.00481"},{"key":"28_CR9","doi-asserted-by":"crossref","unstructured":"Eigen, D., Fergus, R.: Predicting depth, surface normals and semantic labels with a common multi-scale convolutional architecture. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2650\u20132658 (2015)","DOI":"10.1109\/ICCV.2015.304"},{"key":"28_CR10","doi-asserted-by":"crossref","unstructured":"Han, X., Li, Z., Huang, H., Kalogerakis, E., Yu, Y.: High resolution shape completion using deep neural networks for global structure and local geometry inference. In: IEEE International Conference on Computer Vision (ICCV) (2017)","DOI":"10.1109\/ICCV.2017.19"},{"key":"28_CR11","doi-asserted-by":"crossref","unstructured":"Handa, A., Patraucean, V., Badrinarayanan, V., Stent, S., Cipolla, R.: SceneNet: understanding real world indoor scenes with synthetic data. arXiv preprint arXiv:1511.07041 (2015)","DOI":"10.1109\/CVPR.2016.442"},{"key":"28_CR12","doi-asserted-by":"crossref","unstructured":"H\u00e4ne, C., Tulsiani, S., Malik, J.: Hierarchical surface prediction for 3D object reconstruction. arXiv preprint arXiv:1704.00710 (2017)","DOI":"10.1109\/3DV.2017.00054"},{"key":"28_CR13","doi-asserted-by":"crossref","unstructured":"Hane, C., Zach, C., Cohen, A., Angst, R., Pollefeys, M.: Joint 3D scene reconstruction and class segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 97\u2013104 (2013)","DOI":"10.1109\/CVPR.2013.20"},{"key":"28_CR14","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask R-CNN. In: 2017 IEEE International Conference on Computer Vision (ICCV), pp. 2980\u20132988. IEEE (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"28_CR15","doi-asserted-by":"crossref","unstructured":"Hermans, A., Floros, G., Leibe, B.: Dense 3D semantic mapping of indoor scenes from RGB-D images. In: 2014 IEEE International Conference on Robotics and Automation (ICRA), pp. 2631\u20132638. IEEE (2014)","DOI":"10.1109\/ICRA.2014.6907236"},{"key":"28_CR16","doi-asserted-by":"crossref","unstructured":"Ji, M., Gall, J., Zheng, H., Liu, Y., Fang, L.: SurfaceNet: an end-to-end 3D neural network for multiview stereopsis. arXiv preprint arXiv:1708.01749 (2017)","DOI":"10.1109\/ICCV.2017.253"},{"issue":"11","key":"28_CR17","doi-asserted-by":"publisher","first-page":"1241","DOI":"10.1109\/TVCG.2015.2459891","volume":"21","author":"O K\u00e4hler","year":"2015","unstructured":"K\u00e4hler, O., Prisacariu, V.A., Ren, C.Y., Sun, X., Torr, P., Murray, D.: Very high frame rate volumetric integration of depth images on mobile devices. IEEE Trans. Vis. Comput. Gr. 21(11), 1241\u20131250 (2015)","journal-title":"IEEE Trans. Vis. Comput. Gr."},{"key":"28_CR18","doi-asserted-by":"crossref","unstructured":"Kalogerakis, E., Averkiou, M., Maji, S., Chaudhuri, S.: 3D shape segmentation with projective convolutional networks. In: Proceedings of CVPR. IEEE 2 (2017)","DOI":"10.1109\/CVPR.2017.702"},{"key":"28_CR19","unstructured":"Kar, A., H\u00e4ne, C., Malik, J.: Learning a multi-view stereo machine. In: Advances in Neural Information Processing Systems, pp. 364\u2013375 (2017)"},{"key":"28_CR20","doi-asserted-by":"crossref","unstructured":"Kendall, A., Martirosyan, H., Dasgupta, S., Henry, P., Kennedy, R., Bachrach, A., Bry, A.: End-to-end learning of geometry and context for deep stereo regression. CoRR, abs\/1703.04309 (2017)","DOI":"10.1109\/ICCV.2017.17"},{"key":"28_CR21","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"703","DOI":"10.1007\/978-3-319-10599-4_45","volume-title":"Computer Vision \u2013 ECCV 2014","author":"A Kundu","year":"2014","unstructured":"Kundu, A., Li, Y., Dellaert, F., Li, F., Rehg, J.M.: Joint semantic segmentation and 3D reconstruction from monocular video. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8694, pp. 703\u2013718. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10599-4_45"},{"key":"28_CR22","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 3431\u20133440 (2015)","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"28_CR23","doi-asserted-by":"crossref","unstructured":"Maturana, D., Scherer, S.: VoxNet: A 3D convolutional neural network for real-time object recognition. In: 2015 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 922\u2013928. IEEE (2015)","DOI":"10.1109\/IROS.2015.7353481"},{"key":"28_CR24","doi-asserted-by":"crossref","unstructured":"McCormac, J., Handa, A., Davison, A., Leutenegger, S.: SemanticFusion: dense 3D semantic mapping with convolutional neural networks. In: 2017 IEEE International Conference on Robotics and Automation (ICRA), pp. 4628\u20134635. IEEE (2017)","DOI":"10.1109\/ICRA.2017.7989538"},{"key":"28_CR25","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"746","DOI":"10.1007\/978-3-642-33715-4_54","volume-title":"Computer Vision \u2013 ECCV 2012","author":"N Silberman","year":"2012","unstructured":"Silberman, N., Hoiem, D., Kohli, P., Fergus, R.: Indoor segmentation and support inference from RGBD images. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012. LNCS, vol. 7576, pp. 746\u2013760. Springer, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-33715-4_54"},{"key":"28_CR26","doi-asserted-by":"crossref","unstructured":"Newcombe, R.A., et al.: KinectFusion: real-time dense surface mapping and tracking. In: 2011 10th IEEE international symposium on Mixed and Augmented Reality (ISMAR), pp. 127\u2013136. IEEE (2011)","DOI":"10.1109\/ISMAR.2011.6092378"},{"key":"28_CR27","first-page":"169","volume":"32","author":"M Nie\u00dfner","year":"2013","unstructured":"Nie\u00dfner, M., Zollh\u00f6fer, M., Izadi, S., Stamminger, M.: Real-time 3D reconstruction at scale using voxel hashing. ACM Trans. Gr. (TOG) 32, 169 (2013)","journal-title":"ACM Trans. Gr. (TOG)"},{"key":"28_CR28","unstructured":"Paszke, A., Chaurasia, A., Kim, S., Culurciello, E.: ENet: a deep neural network architecture for real-time semantic segmentation. arXiv preprint arXiv:1606.02147 (2016)"},{"key":"28_CR29","unstructured":"Qi, C.R., Su, H., Mo, K., Guibas, L.J.: PointNet: deep learning on point sets for 3D classification and segmentation. In: Proceedings of Computer Vision and Pattern Recognition (CVPR), vol. 1, no. 2, p. 4. IEEE (2017)"},{"key":"28_CR30","doi-asserted-by":"crossref","unstructured":"Qi, C.R., Su, H., Nie\u00dfner, M., Dai, A., Yan, M., Guibas, L.: Volumetric and multi-view CNNs for object classification on 3D data. In: Proceedings of Computer Vision and Pattern Recognition (CVPR). IEEE (2016)","DOI":"10.1109\/CVPR.2016.609"},{"key":"28_CR31","unstructured":"Qi, C.R., Yi, L., Su, H., Guibas, L.J.: PointNet++: deep hierarchical feature learning on point sets in a metric space. In: Advances in Neural Information Processing Systems, pp. 5105\u20135114 (2017)"},{"key":"28_CR32","doi-asserted-by":"crossref","unstructured":"Riegler, G., Ulusoy, A.O., Bischof, H., Geiger, A.: OctNetFusion: learning depth fusion from data. arXiv preprint arXiv:1704.01047 (2017)","DOI":"10.1109\/3DV.2017.00017"},{"key":"28_CR33","doi-asserted-by":"crossref","unstructured":"Riegler, G., Ulusoy, A.O., Geiger, A.: OctNet: learning deep 3D representations at high resolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2017)","DOI":"10.1109\/CVPR.2017.701"},{"key":"28_CR34","doi-asserted-by":"crossref","unstructured":"Savinov, N., Ladicky, L., Hane, C., Pollefeys, M.: Discrete optimization of ray potentials for semantic 3D reconstruction. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5511\u20135518 (2015)","DOI":"10.1109\/CVPR.2015.7299190"},{"key":"28_CR35","doi-asserted-by":"crossref","unstructured":"Silberman, N., Fergus, R.: Indoor scene segmentation using a structured light sensor. In: Proceedings of the International Conference on Computer Vision - Workshop on 3D Representation and Recognition (2011)","DOI":"10.1109\/ICCVW.2011.6130298"},{"key":"28_CR36","doi-asserted-by":"crossref","unstructured":"Song, S., Yu, F., Zeng, A., Chang, A.X., Savva, M., Funkhouser, T.: Semantic scene completion from a single depth image. In: Proceedings of 30th IEEE Conference on Computer Vision and Pattern Recognition (2017)","DOI":"10.1109\/CVPR.2017.28"},{"key":"28_CR37","doi-asserted-by":"crossref","unstructured":"Su, H., Maji, S., Kalogerakis, E., Learned-Miller, E.: Multi-view convolutional neural networks for 3D shape recognition. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 945\u2013953 (2015)","DOI":"10.1109\/ICCV.2015.114"},{"key":"28_CR38","doi-asserted-by":"crossref","unstructured":"Tatarchenko, M., Dosovitskiy, A., Brox, T.: Octree generating networks: efficient convolutional architectures for high-resolution 3D outputs. arXiv preprint arXiv:1703.09438 (2017)","DOI":"10.1109\/ICCV.2017.230"},{"key":"28_CR39","doi-asserted-by":"crossref","unstructured":"Tulsiani, S., Zhou, T., Efros, A.A., Malik, J.: Multi-view supervision for single-view reconstruction via differentiable ray consistency. In: CVPR. vol. 1, p. 3 (2017)","DOI":"10.1109\/CVPR.2017.30"},{"issue":"5","key":"28_CR40","first-page":"154","volume":"34","author":"J Valentin","year":"2015","unstructured":"Valentin, J., et al.: SemanticPaint: interactive 3D labeling and learning at your fingertips. ACM Trans. Gr. (TOG) 34(5), 154 (2015)","journal-title":"ACM Trans. Gr. (TOG)"},{"key":"28_CR41","doi-asserted-by":"crossref","unstructured":"Vineet, V., et al.: Incremental dense semantic stereo fusion for large-scale semantic scene reconstruction. In: 2015 IEEE International Conference on Robotics and Automation (ICRA), pp. 75\u201382. IEEE (2015)","DOI":"10.1109\/ICRA.2015.7138983"},{"issue":"4","key":"28_CR42","first-page":"72","volume":"36","author":"PS Wang","year":"2017","unstructured":"Wang, P.S., Liu, Y., Guo, Y.X., Sun, C.Y., Tong, X.: O-CNN: octree-based convolutional neural networks for 3D shape analysis. ACM Trans. Gr. (TOG) 36(4), 72 (2017)","journal-title":"ACM Trans. Gr. (TOG)"},{"key":"28_CR43","doi-asserted-by":"crossref","unstructured":"Wu, Z., et al.: 3D shapeNets: a deep representation for volumetric shapes. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1912\u20131920 (2015)","DOI":"10.1109\/CVPR.2015.7298801"},{"key":"28_CR44","unstructured":"Yu, F., Koltun, V.: Multi-scale context aggregation by dilated convolutions. arXiv preprint arXiv:1511.07122 (2015)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2018"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-01249-6_28","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,24]],"date-time":"2026-03-24T15:12:06Z","timestamp":1774365126000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-01249-6_28"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783030012489","9783030012496"],"references-count":44,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-01249-6_28","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018]]},"assertion":[{"value":"6 October 2018","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":"Munich","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Germany","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2018","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 September 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 September 2018","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2018.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}