{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T16:07:27Z","timestamp":1781885247690,"version":"3.54.5"},"publisher-location":"Cham","reference-count":72,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030012304","type":"print"},{"value":"9783030012311","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\/978-3-030-01231-1_28","type":"book-chapter","created":{"date-parts":[[2018,10,5]],"date-time":"2018-10-05T16:03:25Z","timestamp":1538755405000},"page":"453-471","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":182,"title":["OmniDepth: Dense Depth Estimation for\u00a0Indoors Spherical Panoramas"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7898-9344","authenticated-orcid":false,"given":"Nikolaos","family":"Zioulis","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0328-8671","authenticated-orcid":false,"given":"Antonis","family":"Karakottas","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dimitrios","family":"Zarpalas","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Petros","family":"Daras","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":"Tateno, K., Tombari, F., Laina, I., Navab, N.: CNN-SLAM: real-time dense monocular slam with learned depth prediction. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). pp. 6565\u20136574, July 2017","DOI":"10.1109\/CVPR.2017.695"},{"key":"28_CR2","unstructured":"Mo, K., Li, H., Lin, Z., Lee, J.Y.: The AdobeIndoorNav dataset: towards deep reinforcement learning based real-world indoor robot visual navigation (2018)"},{"issue":"6","key":"28_CR3","doi-asserted-by":"publisher","first-page":"234","DOI":"10.1145\/3130800.3130828","volume":"36","author":"P Hedman","year":"2017","unstructured":"Hedman, P., Alsisan, S., Szeliski, R., Kopf, J.: Casual 3D photography. ACM Trans. Graph. (TOG) 36(6), 234 (2017)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"28_CR4","doi-asserted-by":"crossref","unstructured":"Huang, J., Chen, Z., Ceylan, D., Jin, H.: 6-DOF VR videos with a single 360-camera. In: 2017 IEEE Virtual Reality (VR), pp. 37\u201344. IEEE (2017)","DOI":"10.1109\/VR.2017.7892229"},{"issue":"3","key":"28_CR5","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1145\/2602146","volume":"33","author":"K Karsch","year":"2014","unstructured":"Karsch, K.: Automatic scene inference for 3D object compositing. ACM Trans. Graph. (TOG) 33(3), 32 (2014)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"28_CR6","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_CR7","doi-asserted-by":"crossref","unstructured":"Ren, X., Bo, L., Fox, D.: RGB-(D) scene labeling: features and algorithms. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2759\u20132766. IEEE (2012)","DOI":"10.1109\/CVPR.2012.6247999"},{"key":"28_CR8","volume-title":"Multiple View Geometry in Computer Vision","author":"R Hartley","year":"2000","unstructured":"Hartley, R., Zisserman, A.: Multiple View Geometry in Computer Vision, 2nd edn. Cambridge University Press, Cambridge (2000)","edition":"2"},{"issue":"1\u20132","key":"28_CR9","first-page":"1","volume":"9","author":"Y Furukawa","year":"2015","unstructured":"Furukawa, Y., Hern\u00e1ndez, C., et al.: Multi-view stereo: a tutorial. Found. Trends\u00ae in Comput. Graph. Vis. 9(1\u20132), 1\u2013148 (2015)","journal-title":"Found. Trends\u00ae in Comput. Graph. Vis."},{"key":"28_CR10","doi-asserted-by":"publisher","first-page":"305","DOI":"10.1017\/S096249291700006X","volume":"26","author":"O \u00d6zye\u015fil","year":"2017","unstructured":"\u00d6zye\u015fil, O., Voroninski, V., Basri, R., Singer, A.: A survey of structure from motion*. Acta Numerica 26, 305\u2013364 (2017)","journal-title":"Acta Numerica"},{"issue":"4","key":"28_CR11","doi-asserted-by":"publisher","first-page":"589","DOI":"10.1109\/TITS.2008.2006736","volume":"9","author":"S Li","year":"2008","unstructured":"Li, S.: Binocular spherical stereo. IEEE Trans. Intell. Transp. Syst. 9(4), 589\u2013600 (2008)","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"28_CR12","unstructured":"Ma, C., Shi, L., Huang, H., Yan, M.: 3D reconstruction from full-view fisheye camera. arXiv preprint arXiv:1506.06273 (2015)"},{"key":"28_CR13","doi-asserted-by":"crossref","unstructured":"Pathak, S., Moro, A., Yamashita, A., Asama, H.: Dense 3D reconstruction from two spherical images via optical flow-based equirectangular epipolar rectification. In: 2016 IEEE International Conference on Imaging Systems and Techniques (IST), pp. 140\u2013145. IEEE (2016)","DOI":"10.1109\/IST.2016.7738212"},{"key":"28_CR14","unstructured":"Li, S., Fukumori, K.: Spherical stereo for the construction of immersive VR environment. In: Proceedings of Virtual Reality, VR 2005, pp. 217\u2013222. IEEE (2005)"},{"issue":"1","key":"28_CR15","doi-asserted-by":"publisher","first-page":"94","DOI":"10.1007\/s11263-013-0616-1","volume":"104","author":"H Kim","year":"2013","unstructured":"Kim, H., Hilton, A.: 3D scene reconstruction from multiple spherical stereo pairs. Int. J. Comput. Vis. 104(1), 94\u2013116 (2013)","journal-title":"Int. J. Comput. Vis."},{"key":"28_CR16","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"668","DOI":"10.1007\/978-3-319-10599-4_43","volume-title":"Computer Vision \u2013 ECCV 2014","author":"Y Zhang","year":"2014","unstructured":"Zhang, Y., Song, S., Tan, P., Xiao, J.: PanoContext: a whole-room 3D context model for panoramic scene understanding. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8694, pp. 668\u2013686. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10599-4_43"},{"key":"28_CR17","doi-asserted-by":"crossref","unstructured":"Yang, H., Zhang, H.: Efficient 3D room shape recovery from a single panorama. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5422\u20135430 (2016)","DOI":"10.1109\/CVPR.2016.585"},{"key":"28_CR18","doi-asserted-by":"crossref","unstructured":"Xu, J., Stenger, B., Kerola, T., Tung, T.: Pano2CAD: room layout from a single panorama image. In: 2017 IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 354\u2013362. IEEE (2017)","DOI":"10.1109\/WACV.2017.46"},{"key":"28_CR19","doi-asserted-by":"crossref","unstructured":"Kim, H., de Campos, T., Hilton, A.: Room layout estimation with object and material attributes information using a spherical camera. In: 2016 Fourth International Conference on 3D Vision (3DV), pp. 519\u2013527. IEEE (2016)","DOI":"10.1109\/3DV.2016.83"},{"issue":"6","key":"28_CR20","doi-asserted-by":"publisher","first-page":"762","DOI":"10.1016\/j.robot.2010.02.008","volume":"58","author":"C Plagemann","year":"2010","unstructured":"Plagemann, C., Stachniss, C., Hess, J., Endres, F., Franklin, N.: A nonparametric learning approach to range sensing from omnidirectional vision. Robot. Auton. Syst. 58(6), 762\u2013772 (2010)","journal-title":"Robot. Auton. Syst."},{"issue":"11","key":"28_CR21","doi-asserted-by":"publisher","first-page":"1199","DOI":"10.1007\/s11263-018-1089-z","volume":"126","author":"M Ruder","year":"2018","unstructured":"Ruder, M., Dosovitskiy, A., Brox, T.: Artistic style transfer for videos and spherical images. Int. J. Comput. Vis. 126(11), 1199\u20131219 (2018)","journal-title":"Int. J. Comput. Vis."},{"key":"28_CR22","doi-asserted-by":"crossref","unstructured":"Monroy, R., Lutz, S., Chalasani, T., Smolic, A.: SalNet360: saliency maps for omni-directional images with CNN. arXiv preprint arXiv:1709.06505 (2017)","DOI":"10.1016\/j.image.2018.05.005"},{"key":"28_CR23","doi-asserted-by":"crossref","unstructured":"Zhang, J., Lalonde, J.F.: Learning high dynamic range from outdoor panoramas. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4519\u20134528 (2017)","DOI":"10.1109\/ICCV.2017.484"},{"key":"28_CR24","doi-asserted-by":"crossref","unstructured":"Frossard, P., Khasanova, R.: Graph-based classification of omnidirectional images. In: 2017 IEEE International Conference on Computer Vision Workshop (ICCVW), pp. 860\u2013869. IEEE (2017)","DOI":"10.1109\/ICCVW.2017.106"},{"key":"28_CR25","unstructured":"Su, Y.C., Grauman, K.: Learning spherical convolution for fast features from 360 imagery. In: Advances in Neural Information Processing Systems, pp. 529\u2013539 (2017)"},{"key":"28_CR26","doi-asserted-by":"crossref","unstructured":"Jeon, Y., Kim, J.: Active convolution: learning the shape of convolution for image classification. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1846\u20131854. IEEE (2017)","DOI":"10.1109\/CVPR.2017.200"},{"key":"28_CR27","doi-asserted-by":"crossref","unstructured":"Dai, J., et al.: Deformable convolutional networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 764\u2013773 (2017)","DOI":"10.1109\/ICCV.2017.89"},{"key":"28_CR28","unstructured":"Deng, L., Yang, M., Li, H., Li, T., Hu, B., Wang, C.: Restricted deformable convolution based road scene semantic segmentation using surround view cameras. arXiv preprint arXiv:1801.00708 (2018)"},{"key":"28_CR29","unstructured":"Cohen, T., Geiger, M., Welling, M.: Convolutional networks for spherical signals. In: Principled Approaches to Deep Learning Workshop ICML 2017 (2017)"},{"key":"28_CR30","unstructured":"Cohen, T.S., Geiger, M., K\u00f6hler, J., Welling, M.: Spherical CNNs. In: International Conference on Learning Representations (ICLR) (2018)"},{"key":"28_CR31","doi-asserted-by":"crossref","unstructured":"Ranftl, R., Vineet, V., Chen, Q., Koltun, V.: Dense monocular depth estimation in complex dynamic scenes. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4058\u20134066 (2016)","DOI":"10.1109\/CVPR.2016.440"},{"key":"28_CR32","doi-asserted-by":"crossref","unstructured":"Liu, M., Salzmann, M., He, X.: Discrete-continuous depth estimation from a single image. In: 2014 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 716\u2013723. IEEE (2014)","DOI":"10.1109\/CVPR.2014.97"},{"key":"28_CR33","doi-asserted-by":"publisher","first-page":"173","DOI":"10.1007\/978-3-319-23048-1_9","volume-title":"Dense Image Correspondences for Computer Vision","author":"K Karsch","year":"2016","unstructured":"Karsch, K., Liu, C., Kang, S.B.: Depth transfer: depth extraction from videos using nonparametric sampling. In: Hassner, T., Liu, C. (eds.) Dense Image Correspondences for Computer Vision, pp. 173\u2013205. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-23048-1_9"},{"key":"28_CR34","unstructured":"Eigen, D., Puhrsch, C., Fergus, R.: Depth map prediction from a single image using a multi-scale deep network. In: Advances in Neural Information Processing Systems, pp. 2366\u20132374 (2014)"},{"key":"28_CR35","doi-asserted-by":"crossref","unstructured":"Ren, Z., Lee, Y.J.: Cross-domain self-supervised multi-task feature learning using synthetic imagery. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2018)","DOI":"10.1109\/CVPR.2018.00086"},{"key":"28_CR36","doi-asserted-by":"crossref","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)","DOI":"10.1109\/3DV.2016.32"},{"key":"28_CR37","doi-asserted-by":"crossref","unstructured":"Li, B., Shen, C., Dai, Y., van den Hengel, A., He, M.: Depth and surface normal estimation from monocular images using regression on deep features and hierarchical CRFs. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1119\u20131127 (2015)","DOI":"10.1109\/CVPR.2015.7298715"},{"issue":"10","key":"28_CR38","doi-asserted-by":"publisher","first-page":"2024","DOI":"10.1109\/TPAMI.2015.2505283","volume":"38","author":"F Liu","year":"2016","unstructured":"Liu, F., Shen, C., Lin, G., Reid, I.: Learning depth from single monocular images using deep convolutional neural fields. IEEE Trans. Pattern Anal. Mach. Intell. 38(10), 2024\u20132039 (2016)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"28_CR39","doi-asserted-by":"crossref","unstructured":"Xu, D., Ricci, E., Ouyang, W., Wang, X., Sebe, N.: Multi-scale continuous CRFs as sequential deep networks for monocular depth estimation. In: Proceedings of CVPR (2017)","DOI":"10.1109\/CVPR.2017.25"},{"key":"28_CR40","unstructured":"Chakrabarti, A., Shao, J., Shakhnarovich, G.: Depth from a single image by harmonizing overcomplete local network predictions. In: Advances in Neural Information Processing Systems, pp. 2658\u20132666 (2016)"},{"key":"28_CR41","doi-asserted-by":"publisher","first-page":"328","DOI":"10.1016\/j.patcog.2018.05.029","volume":"83","author":"B Li","year":"2018","unstructured":"Li, B., Dai, Y., He, M.: Monocular depth estimation with hierarchical fusion of dilated CNNs and soft-weighted-sum inference. Pattern Recogn. 83, 328\u2013339 (2018)","journal-title":"Pattern Recogn."},{"key":"28_CR42","doi-asserted-by":"crossref","unstructured":"Cao, Y., Wu, Z., Shen, C.: Estimating depth from monocular images as classification using deep fully convolutional residual networks. IEEE Trans. Circ. Syst. Video Technol. (2017)","DOI":"10.1109\/TCSVT.2017.2740321"},{"key":"28_CR43","unstructured":"Fu, H., Gong, M., Wang, C., Tao, D.: A compromise principle in deep monocular depth estimation. arXiv preprint arXiv:1708.08267 (2017)"},{"key":"28_CR44","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-46484-8_45","volume-title":"Computer Vision \u2013 ECCV 2016","author":"R Garg","year":"2016","unstructured":"Garg, R., B.G., V.K., Carneiro, G., Reid, I.: Unsupervised CNN for single view depth estimation: geometry to the rescue. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9912, pp. 740\u2013756. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46484-8_45"},{"key":"28_CR45","doi-asserted-by":"crossref","unstructured":"Godard, C., Mac Aodha, O., Brostow, G.J.: Unsupervised monocular depth estimation with left-right consistency. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.699"},{"key":"28_CR46","doi-asserted-by":"crossref","unstructured":"Zhou, T., Brown, M., Snavely, N., Lowe, D.G.: Unsupervised learning of depth and ego-motion from video. In: CVPR, vol. 2, p. 7 (2017)","DOI":"10.1109\/CVPR.2017.700"},{"key":"28_CR47","doi-asserted-by":"crossref","unstructured":"Wang, C., Buenaposada, J.M., Zhu, R., Lucey, S.: Learning depth from monocular videos using direct methods. IEEE Conference on Computer Vision and Pattern Recognition (2018)","DOI":"10.1109\/CVPR.2018.00216"},{"key":"28_CR48","doi-asserted-by":"crossref","unstructured":"Mahjourian, R., Wicke, M., Angelova, A.: Unsupervised learning of depth and ego-motion from monocular video using 3D geometric constraints. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2018)","DOI":"10.1109\/CVPR.2018.00594"},{"key":"28_CR49","doi-asserted-by":"crossref","unstructured":"Yang, Z., Wang, P., Xu, W., Zhao, L., Nevatia, R.: Unsupervised learning of geometry with edge-aware depth-normal consistency. arXiv preprint arXiv:1711.03665 (2017)","DOI":"10.1609\/aaai.v32i1.12257"},{"key":"28_CR50","doi-asserted-by":"crossref","unstructured":"Yin, Z., Shi, J.: GeoNet: unsupervised learning of dense depth, optical flow and camera pose. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2018)","DOI":"10.1109\/CVPR.2018.00212"},{"key":"28_CR51","doi-asserted-by":"crossref","unstructured":"Srinivasan, P.P., Garg, R., Wadhwa, N., Ng, R., Barron, J.T.: Aperture supervision for monocular depth estimation (2017)","DOI":"10.1109\/CVPR.2018.00669"},{"key":"28_CR52","unstructured":"Chen, W., Fu, Z., Yang, D., Deng, J.: Single-image depth perception in the wild. In: Advances in Neural Information Processing Systems, pp. 730\u2013738 (2016)"},{"key":"28_CR53","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"},{"issue":"5","key":"28_CR54","doi-asserted-by":"publisher","first-page":"824","DOI":"10.1109\/TPAMI.2008.132","volume":"31","author":"A Saxena","year":"2009","unstructured":"Saxena, A., Sun, M., Ng, A.Y.: Make3D: learning 3D scene structure from a single still image. IEEE Trans. Pattern Anal. Mach. Intell. 31(5), 824\u2013840 (2009)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"4","key":"28_CR55","doi-asserted-by":"publisher","first-page":"148","DOI":"10.1145\/3072959.3073645","volume":"36","author":"K Matzen","year":"2017","unstructured":"Matzen, K., Cohen, M.F., Evans, B., Kopf, J., Szeliski, R.: Low-cost 360 stereo photography and video capture. ACM Trans. Graph. (TOG) 36(4), 148 (2017)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"28_CR56","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: IEEE Conference on Computer Vision and Pattern Recognition (2017)","DOI":"10.1109\/CVPR.2017.28"},{"key":"28_CR57","doi-asserted-by":"crossref","unstructured":"Handa, A., P\u0103tr\u0103ucean, V., Stent, S., Cipolla, R.: SceneNet: an annotated model generator for indoor scene understanding. In: 2016 IEEE International Conference on Robotics and Automation (ICRA), pp. 5737\u20135743. IEEE (2016)","DOI":"10.1109\/ICRA.2016.7487797"},{"key":"28_CR58","unstructured":"Armeni, I., Sax, S., Zamir, A.R., Savarese, S.: Joint 2D-3D-semantic data for indoor scene understanding. arXiv preprint arXiv:1702.01105 (2017)"},{"key":"28_CR59","doi-asserted-by":"crossref","unstructured":"Armeni, I., et al.: 3D semantic parsing of large-scale indoor spaces. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1534\u20131543 (2016)","DOI":"10.1109\/CVPR.2016.170"},{"key":"28_CR60","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_CR61","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_CR62","unstructured":"Clevert, D.A., Unterthiner, T., Hochreiter, S.: Fast and accurate deep network learning by exponential linear units (ELUs). arXiv preprint arXiv:1511.07289 (2015)"},{"key":"28_CR63","unstructured":"Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. In: International Conference on Machine Learning, pp. 448\u2013456 (2015)"},{"key":"28_CR64","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"28_CR65","doi-asserted-by":"crossref","unstructured":"Yu, F., Koltun, V., Funkhouser, T.: Dilated residual networks. In: Computer Vision and Pattern Recognition, vol. 1 (2017)","DOI":"10.1109\/CVPR.2017.75"},{"key":"28_CR66","unstructured":"van Noord, N., Postma, E.O.: Light-weight pixel context encoders for image inpainting. CoRR abs\/1801.05585 (2018)"},{"issue":"1","key":"28_CR67","first-page":"1929","volume":"15","author":"N Srivastava","year":"2014","unstructured":"Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15(1), 1929\u20131958 (2014)","journal-title":"J. Mach. Learn. Res."},{"key":"28_CR68","doi-asserted-by":"crossref","unstructured":"Jia, Y., et al.: Caffe: convolutional architecture for fast feature embedding. In: Proceedings of the 22nd ACM International Conference on Multimedia, MM 2014, pp. 675\u2013678. ACM, New York (2014)","DOI":"10.1145\/2647868.2654889"},{"key":"28_CR69","unstructured":"Glorot, X., Bengio, Y.: Understanding the difficulty of training deep feedforward neural networks. In: Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics, Proceedings of Machine Learning Research, vol. 9. PMLR, pp. 249\u2013256, 13\u201315 May 2010"},{"key":"28_CR70","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"28_CR71","doi-asserted-by":"crossref","unstructured":"Xiao, J., Ehinger, K.A., Oliva, A., Torralba, A.: Recognizing scene viewpoint using panoramic place representation. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2695\u20132702. IEEE (2012)","DOI":"10.1109\/CVPR.2012.6247991"},{"issue":"4","key":"28_CR72","doi-asserted-by":"publisher","first-page":"1379","DOI":"10.1109\/TVCG.2017.2657178","volume":"23","author":"T Rhee","year":"2017","unstructured":"Rhee, T., Petikam, L., Allen, B., Chalmers, A.: MR360: mixed reality rendering for 360 panoramic videos. IEEE Trans. Visual. Comput. Graph. 23(4), 1379\u20131388 (2017)","journal-title":"IEEE Trans. Visual. Comput. Graph."}],"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\/978-3-030-01231-1_28","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T18:37:10Z","timestamp":1775241430000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-01231-1_28"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783030012304","9783030012311"],"references-count":72,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-01231-1_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"}]}}