{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,27]],"date-time":"2026-06-27T05:08:53Z","timestamp":1782536933925,"version":"3.54.5"},"publisher-location":"Cham","reference-count":50,"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_10","type":"book-chapter","created":{"date-parts":[[2018,10,5]],"date-time":"2018-10-05T15:35:46Z","timestamp":1538753746000},"page":"155-171","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":55,"title":["DDRNet: Depth Map Denoising and Refinement for Consumer Depth Cameras Using Cascaded CNNs"],"prefix":"10.1007","author":[{"given":"Shi","family":"Yan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chenglei","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lizhen","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Feng","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liang","family":"An","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kaiwen","family":"Guo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yebin","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2018,10,6]]},"reference":[{"key":"10_CR1","doi-asserted-by":"crossref","unstructured":"Barron, J.T., Malik, J.: Intrinsic scene properties from a single RGB-D image. In: Proceedings of CVPR, pp. 17\u201324. IEEE (2013)","DOI":"10.1109\/CVPR.2013.10"},{"key":"10_CR2","doi-asserted-by":"crossref","unstructured":"Barron, J.T., Malik, J.: Shape, illumination, and reflectance from shading. Technical report, EECS, UC Berkeley, May 2013","DOI":"10.21236\/ADA586648"},{"issue":"4","key":"10_CR3","doi-asserted-by":"publisher","first-page":"40:1","DOI":"10.1145\/1778765.1778777","volume":"29","author":"T Beeler","year":"2010","unstructured":"Beeler, T., Bickel, B., Beardsley, P.A., Sumner, B., Gross, M.H.: High-quality single-shot capture of facial geometry. ACM Trans. Graph. 29(4), 40:1\u201340:9 (2010)","journal-title":"ACM Trans. Graph."},{"key":"10_CR4","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"30","DOI":"10.1007\/978-3-642-33718-5_3","volume-title":"Computer Vision \u2013 ECCV 2012","author":"T Beeler","year":"2012","unstructured":"Beeler, T., Bradley, D., Zimmer, H., Gross, M.: Improved reconstruction of deforming surfaces by cancelling ambient occlusion. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012. LNCS, vol. 7572, pp. 30\u201343. Springer, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-33718-5_3"},{"key":"10_CR5","unstructured":"Besl, P.J., McKay, N.D.: Method for registration of 3-D shapes. In: Robotics-DL Tentative, pp. 586\u2013606. International Society for Optics and Photonics (1992)"},{"key":"10_CR6","unstructured":"Chan, D., Buisman, H., Theobalt, C., Thrun, S.: A noise-aware filter for real-time depth upsampling. In: ECCV Workshop on Multi-camera & Multi-modal Sensor Fusion (2008)"},{"issue":"4","key":"10_CR7","first-page":"113:1","volume":"32","author":"J Chen","year":"2013","unstructured":"Chen, J., Bautembach, D., Izadi, S.: Scalable real-time volumetric surface reconstruction. ACM Trans. Graph. 32(4), 113:1\u2013113:16 (2013)","journal-title":"ACM Trans. Graph."},{"issue":"5","key":"10_CR8","doi-asserted-by":"publisher","first-page":"1039","DOI":"10.1109\/TPAMI.2012.190","volume":"35","author":"Y Cui","year":"2013","unstructured":"Cui, Y., Schuon, S., Thrun, S., Stricker, D., Theobalt, C.: Algorithms for 3D shape scanning with a depth camera. IEEE Trans. Pattern Anal. Mach. Intell. 35(5), 1039\u20131050 (2013)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10_CR9","unstructured":"Diebel, J., Thrun, S.: An application of Markov random fields to range sensing. In: Proceedings of the 18th International Conference on Neural Information Processing Systems, NIPS 2005, pp. 291\u2013298. MIT Press, Cambridge (2005)"},{"key":"10_CR10","doi-asserted-by":"crossref","unstructured":"Dolson, J., Baek, J., Plagemann, C., Thrun, S.: Upsampling range data in dynamic environments. In: 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 1141\u20131148, June 2010","DOI":"10.1109\/CVPR.2010.5540086"},{"issue":"3","key":"10_CR11","doi-asserted-by":"publisher","first-page":"32:1","DOI":"10.1145\/3083722","volume":"36","author":"K Guo","year":"2017","unstructured":"Guo, K., Xu, F., Yu, T., Liu, X., Dai, Q., Liu, Y.: Real-time geometry, albedo, and motion reconstruction using a single RGB-D camera. ACM Trans. Graph. 36(3), 32:1\u201332:13 (2017)","journal-title":"ACM Trans. Graph."},{"key":"10_CR12","doi-asserted-by":"crossref","unstructured":"Han, Y., Lee, J.Y., Kweon, I.S.: High quality shape from a single RGB-D image under uncalibrated natural illumination. In: Proceedings of ICCV (2013)","DOI":"10.1109\/ICCV.2013.204"},{"key":"10_CR13","doi-asserted-by":"crossref","unstructured":"Han, Y., Lee, J.Y., Kweon, I.S.: High quality shape from a single RGB-D image under uncalibrated natural illumination. In: IEEE International Conference on Computer Vision, pp. 1617\u20131624 (2013)","DOI":"10.1109\/ICCV.2013.204"},{"key":"10_CR14","doi-asserted-by":"crossref","unstructured":"Hariharan, B., Arbelaez, P., Girshick, R., Malik, J.: Hypercolumns for object segmentation and fine-grained localization, pp. 447\u2013456 (2014)","DOI":"10.1109\/CVPR.2015.7298642"},{"issue":"6","key":"10_CR15","doi-asserted-by":"publisher","first-page":"1397","DOI":"10.1109\/TPAMI.2012.213","volume":"35","author":"K He","year":"2013","unstructured":"He, K., Sun, J., Tang, X.: Guided image filtering. IEEE Trans. Pattern Anal. Mach. Intell. 35(6), 1397\u20131409 (2013)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"5","key":"10_CR16","doi-asserted-by":"publisher","first-page":"647","DOI":"10.1177\/0278364911434148","volume":"31","author":"P Henry","year":"2012","unstructured":"Henry, P., Krainin, M., Herbst, E., Ren, X., Fox, D.: RGB-D mapping: using kinect-style depth cameras for dense 3D modeling of indoor environments. Int. J. Robot. Res. 31(5), 647\u2013663 (2012)","journal-title":"Int. J. Robot. Res."},{"key":"10_CR17","unstructured":"Horn, B.K.: Obtaining shape from shading information. In: The Psychology of Computer Vision, pp. 115\u2013155 (1975)"},{"key":"10_CR18","doi-asserted-by":"crossref","unstructured":"Isola, P., Zhu, J.Y., Zhou, T., Efros, A.A.: Image-to-image translation with conditional adversarial networks (2016)","DOI":"10.1109\/CVPR.2017.632"},{"key":"10_CR19","doi-asserted-by":"crossref","unstructured":"Izadi, S., et al.: KinectFusion: real-time 3D reconstruction and interaction using a moving depth camera. In: Proceedings of UIST, pp. 559\u2013568. ACM (2011)","DOI":"10.1145\/2047196.2047270"},{"key":"10_CR20","doi-asserted-by":"crossref","unstructured":"Kajiya, J.T.: The rendering equation. In: Proceedings of the 13th Annual Conference on Computer Graphics and Interactive Techniques, SIGGRAPH 1986, pp. 143\u2013150. ACM, New York (1986)","DOI":"10.1145\/15886.15902"},{"key":"10_CR21","doi-asserted-by":"crossref","unstructured":"Khan, N., Tran, L., Tappen, M.: Training many-parameter shape-from-shading models using a surface database. In: Proceedings of ICCV Workshop (2009)","DOI":"10.1109\/ICCVW.2009.5457444"},{"issue":"3","key":"10_CR22","doi-asserted-by":"publisher","first-page":"96","DOI":"10.1145\/1276377.1276497","volume":"26","author":"J Kopf","year":"2007","unstructured":"Kopf, J., Cohen, M.F., Lischinski, D., Uyttendaele, M.: Joint bilateral upsampling. ACM Trans. Graph. 26(3), 96 (2007)","journal-title":"ACM Trans. Graph."},{"key":"10_CR23","doi-asserted-by":"crossref","unstructured":"Lindner, M., Kolb, A., Hartmann, K.: Data-fusion of PMD-based distance-information and high-resolution RGB-images. In: 2007 International Symposium on Signals, Circuits and Systems, vol. 1, pp. 1\u20134, July 2007","DOI":"10.1109\/ISSCS.2007.4292666"},{"key":"10_CR24","doi-asserted-by":"crossref","unstructured":"Mayer, N., et al.: A large dataset to train convolutional networks for disparity, optical flow, and scene flow estimation. In: Computer Vision and Pattern Recognition, pp. 4040\u20134048 (2016)","DOI":"10.1109\/CVPR.2016.438"},{"key":"10_CR25","doi-asserted-by":"crossref","unstructured":"Nestmeyer, T., Gehler, P.V.: Reflectance adaptive filtering improves intrinsic image estimation. In: CVPR, pp. 1771\u20131780 (2017)","DOI":"10.1109\/CVPR.2017.192"},{"key":"10_CR26","doi-asserted-by":"crossref","unstructured":"Newcombe, R.A., Fox, D., Seitz, S.M.: Dynamicfusion: reconstruction and tracking of non-rigid scenes in real-time. In: 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 343\u2013352, June 2015","DOI":"10.1109\/CVPR.2015.7298631"},{"key":"10_CR27","doi-asserted-by":"crossref","unstructured":"Newcombe, R.A., Izadi, S., et al.: KinectFusion: real-time dense surface mapping and tracking. In: IEEE International Symposium on Mixed and Augmented Reality (ISMAR), pp. 127\u2013136 (2011)","DOI":"10.1109\/ISMAR.2011.6092378"},{"issue":"6","key":"10_CR28","doi-asserted-by":"publisher","first-page":"169","DOI":"10.1145\/2508363.2508374","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. Graph. (TOG) 32(6), 169 (2013)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"10_CR29","doi-asserted-by":"crossref","unstructured":"Odena, A., Dumoulin, V., Olah, C.: Deconvolution and checkerboard artifacts. Distill (2016)","DOI":"10.23915\/distill.00003"},{"key":"10_CR30","doi-asserted-by":"crossref","unstructured":"Or El, R., Rosman, G., Wetzler, A., Kimmel, R., Bruckstein, A.M.: RGBD-fusion: real-time high precision depth recovery. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2015","DOI":"10.1109\/CVPR.2015.7299179"},{"key":"10_CR31","doi-asserted-by":"crossref","unstructured":"Park, J., Kim, H., Tai, Y.W., Brown, M.S., Kweon, I.: High quality depth map upsampling for 3D-TOF cameras. In: 2011 International Conference on Computer Vision, pp. 1623\u20131630, November 2011","DOI":"10.1109\/ICCV.2011.6126423"},{"key":"10_CR32","unstructured":"RealityCapture (2017). https:\/\/www.capturingreality.com\/"},{"key":"10_CR33","doi-asserted-by":"crossref","unstructured":"Richardson, E., Sela, M., Or-El, R., Kimmel, R.: Learning detailed face reconstruction from a single image. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.589"},{"issue":"2pt1","key":"10_CR34","doi-asserted-by":"publisher","first-page":"247","DOI":"10.1111\/j.1467-8659.2012.03003.x","volume":"31","author":"C Richardt","year":"2012","unstructured":"Richardt, C., Stoll, C., Dodgson, N.A., Seidel, H.P., Theobalt, C.: Coherent spatiotemporal filtering, upsampling and rendering of RGBZ videos. Comput. Graph. Forum 31(2pt1), 247\u2013256 (2012)","journal-title":"Comput. Graph. Forum"},{"key":"10_CR35","doi-asserted-by":"crossref","unstructured":"Riegler, G., Ulusoy, A.O., Bischof, H., Geiger, A.: OctNetFusion: learning depth fusion from data. In: 2017 International Conference on 3D Vision (3DV), pp. 57\u201366. IEEE (2017)","DOI":"10.1109\/3DV.2017.00017"},{"key":"10_CR36","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"234","DOI":"10.1007\/978-3-319-24574-4_28","volume-title":"Medical Image Computing and Computer-Assisted Intervention \u2013 MICCAI 2015","author":"O Ronneberger","year":"2015","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: U-net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234\u2013241. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-24574-4_28"},{"key":"10_CR37","doi-asserted-by":"crossref","unstructured":"Sela, M., Richardson, E., Kimmel, R.: Unrestricted facial geometry reconstruction using image-to-image translation (2017)","DOI":"10.1109\/ICCV.2017.175"},{"key":"10_CR38","doi-asserted-by":"crossref","unstructured":"Tewari, A., et al.: MoFA: model-based deep convolutional face autoencoder for unsupervised monocular reconstruction. In: The IEEE International Conference on Computer Vision (ICCV), vol. 2, p. 5 (2017)","DOI":"10.1109\/ICCV.2017.401"},{"key":"10_CR39","doi-asserted-by":"crossref","unstructured":"Varol, G., et al.: Learning from synthetic humans. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.492"},{"issue":"4","key":"10_CR40","doi-asserted-by":"publisher","first-page":"985","DOI":"10.1109\/72.508940","volume":"7","author":"G Wei","year":"1996","unstructured":"Wei, G., Hirzinger, G.: Learning shape from shading by a multilayer network. IEEE Trans. Neural Netw. 7(4), 985\u2013995 (1996)","journal-title":"IEEE Trans. Neural Netw."},{"key":"10_CR41","doi-asserted-by":"crossref","unstructured":"Wojna, Z., et al.: The devil is in the decoder (2017)","DOI":"10.5244\/C.31.10"},{"issue":"6","key":"10_CR42","first-page":"161","volume":"32","author":"C Wu","year":"2013","unstructured":"Wu, C., Stoll, C., Valgaerts, L., Theobalt, C.: On-set performance capture of multiple actors with a stereo camera. ACM Trans. Graph. (TOG) 32(6), 161 (2013)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"10_CR43","doi-asserted-by":"crossref","unstructured":"Wu, C., Varanasi, K., Liu, Y., Seidel, H., Theobalt, C.: Shading-based dynamic shape refinement from multi-view video under general illumination, pp. 1108\u20131115 (2011)","DOI":"10.1109\/ICCV.2011.6126358"},{"issue":"6","key":"10_CR44","first-page":"200","volume":"33","author":"C Wu","year":"2014","unstructured":"Wu, C., Zollh\u00f6fer, M., Nie\u00dfner, M., Stamminger, M., Izadi, S., Theobalt, C.: Real-time shading-based refinement for consumer depth cameras. ACM Trans. Graph. (TOG) 33(6), 200 (2014)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"10_CR45","doi-asserted-by":"crossref","unstructured":"Yang, Q., Yang, R., Davis, J., Nister, D.: Spatial-depth super resolution for range images. In: 2007 IEEE Conference on Computer Vision and Pattern Recognition, pp. 1\u20138, June 2007","DOI":"10.1109\/CVPR.2007.383211"},{"key":"10_CR46","doi-asserted-by":"crossref","unstructured":"Yu, L., Yeung, S., Tai, Y., Lin, S.: Shading-based shape refinement of RGB-D images, pp. 1415\u20131422 (2013)","DOI":"10.1109\/CVPR.2013.186"},{"key":"10_CR47","doi-asserted-by":"crossref","unstructured":"Yu, T., et al.: BodyFusion: real-time capture of human motion and surface geometry using a single depth camera. In: The IEEE International Conference on Computer Vision (ICCV). IEEE, October 2017","DOI":"10.1109\/ICCV.2017.104"},{"key":"10_CR48","doi-asserted-by":"crossref","unstructured":"Yu, T., et al.: DoubleFusion: real-time capture of human performance with inner body shape from a depth sensor. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2018)","DOI":"10.1109\/CVPR.2018.00761"},{"issue":"8","key":"10_CR49","doi-asserted-by":"publisher","first-page":"690","DOI":"10.1109\/34.784284","volume":"21","author":"Z Zhang","year":"1999","unstructured":"Zhang, Z., Tsa, P.S., Cryer, J.E., Shah, M.: Shape from shading: a survey. IEEE PAMI 21(8), 690\u2013706 (1999)","journal-title":"IEEE PAMI"},{"key":"10_CR50","unstructured":"Zhu, J., Wang, L., Yang, R., Davis, J.: Fusion of time-of-flight depth and stereo for high accuracy depth maps. In: 2008 IEEE Conference on Computer Vision and Pattern Recognition, pp. 1\u20138, June 2008"}],"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_10","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,5]],"date-time":"2022-10-05T00:51:28Z","timestamp":1664931088000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-01249-6_10"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783030012489","9783030012496"],"references-count":50,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-01249-6_10","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"}]}}