{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,20]],"date-time":"2025-10-20T10:19:43Z","timestamp":1760955583194,"version":"3.40.3"},"publisher-location":"Cham","reference-count":48,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319249469"},{"type":"electronic","value":"9783319249476"}],"license":[{"start":{"date-parts":[[2015,1,1]],"date-time":"2015-01-01T00:00:00Z","timestamp":1420070400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/2.5"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2015]]},"DOI":"10.1007\/978-3-319-24947-6_15","type":"book-chapter","created":{"date-parts":[[2015,10,6]],"date-time":"2015-10-06T18:10:30Z","timestamp":1444155030000},"page":"183-195","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":32,"title":["Joint 3D Object and Layout Inference from a Single RGB-D Image"],"prefix":"10.1007","author":[{"given":"Andreas","family":"Geiger","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chaohui","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2015,11,3]]},"reference":[{"key":"15_CR1","doi-asserted-by":"crossref","unstructured":"Aubry, M., Maturana, D., Efros, A., Russell, B., Sivic, J.: Seeing 3D chairs: exemplar part-based 2D\u20133D alignment using a large dataset of CAD models. In: CVPR (2014)","DOI":"10.1109\/CVPR.2014.487"},{"key":"15_CR2","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/8579.001.0001","volume-title":"Markov Random Fields for Vision and Image Processing","author":"A Blake","year":"2011","unstructured":"Blake, A., Kohli, P., Rother, C.: Markov Random Fields for Vision and Image Processing. MIT Press, Cambridge (2011)"},{"issue":"7","key":"15_CR3","doi-asserted-by":"publisher","first-page":"1312","DOI":"10.1109\/TPAMI.2011.231","volume":"34","author":"J Carreira","year":"2012","unstructured":"Carreira, J., Sminchisescu, C.: CPMC: automatic object segmentation using constrained parametric min-cuts. PAMI 34(7), 1312\u20131328 (2012)","journal-title":"PAMI"},{"key":"15_CR4","doi-asserted-by":"crossref","unstructured":"Choi, W., Chao, Y.W., Pantofaru, C., Savarese, S.: Understanding indoor scenes using 3D geometric phrases. In: CVPR (2013)","DOI":"10.1109\/CVPR.2013.12"},{"issue":"2","key":"15_CR5","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1007\/s11263-009-0275-4","volume":"88","author":"M Everingham","year":"2010","unstructured":"Everingham, M., Van Gool, L., Williams, C.K.I., Winn, J., Zisserman, A.: The pascal visual object classes (VOC) challenge. IJCV 88(2), 303\u2013338 (2010)","journal-title":"IJCV"},{"key":"15_CR6","doi-asserted-by":"crossref","unstructured":"Felzenszwalb, P.F., Girshick, R.B., McAllester, D.A.: Cascade object detection with deformable part models. In: CVPR (2010)","DOI":"10.1109\/CVPR.2010.5539906"},{"issue":"12","key":"15_CR7","doi-asserted-by":"publisher","first-page":"2549","DOI":"10.1109\/TPAMI.2011.121","volume":"33","author":"PF Felzenszwalb","year":"2011","unstructured":"Felzenszwalb, P.F., Mcauley, J.J.: Fast inference with min-sum matrix product. PAMI 33(12), 2549\u20132554 (2011)","journal-title":"PAMI"},{"key":"15_CR8","doi-asserted-by":"crossref","unstructured":"Fouhey, D.F., Gupta, A., Hebert, M.: Data-driven 3D primitives for single image understanding. In: ICCV (2013)","DOI":"10.1109\/ICCV.2013.421"},{"key":"15_CR9","doi-asserted-by":"publisher","DOI":"10.1201\/b14835","volume-title":"Markov Chain Monte Carlo in Practice","author":"W Gilks","year":"1995","unstructured":"Gilks, W., Richardson, S.: Markov Chain Monte Carlo in Practice. Chapman & Hall, London (1995)"},{"key":"15_CR10","doi-asserted-by":"crossref","unstructured":"Girshick, R., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: CVPR (2014)","DOI":"10.1109\/CVPR.2014.81"},{"key":"15_CR11","doi-asserted-by":"crossref","unstructured":"G\u00fcney, F., Geiger, A.: Displets: resolving stereo ambiguities using object knowledge. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7299044"},{"key":"15_CR12","doi-asserted-by":"crossref","unstructured":"Guo, R., Hoiem, D.: Support surface prediction in indoor scenes. In: ICCV (2013)","DOI":"10.1109\/ICCV.2013.266"},{"key":"15_CR13","doi-asserted-by":"crossref","unstructured":"Gupta, S., Arbelaez, P., Malik, J.: Perceptual organization and recognition of indoor scenes from RGB-D images. In: CVPR (2013)","DOI":"10.1109\/CVPR.2013.79"},{"key":"15_CR14","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"345","DOI":"10.1007\/978-3-319-10584-0_23","volume-title":"Computer Vision \u2013 ECCV 2014","author":"S Gupta","year":"2014","unstructured":"Gupta, S., Girshick, R., Arbel\u00e1ez, P., Malik, J.: Learning rich features from RGB-D images for object detection and segmentation. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014, Part VII. LNCS, vol. 8695, pp. 345\u2013360. Springer, Heidelberg (2014)"},{"key":"15_CR15","doi-asserted-by":"crossref","unstructured":"Hedau, V., Hoiem, D., Forsyth, D.: Recovering the spatial layout of cluttered rooms. In: ICCV (2009)","DOI":"10.1109\/ICCV.2009.5459411"},{"key":"15_CR16","doi-asserted-by":"crossref","unstructured":"Jia, Z., Gallagher, A., Saxena, A., Chen, T.: 3D-based reasoning with blocks, support, and stability. In: CVPR (2013)","DOI":"10.1109\/CVPR.2013.8"},{"key":"15_CR17","doi-asserted-by":"crossref","unstructured":"Jiang, H., Xiao, J.: A linear approach to matching cuboids in RGB-D images. In: CVPR (2013)","DOI":"10.1109\/CVPR.2013.282"},{"key":"15_CR18","doi-asserted-by":"crossref","unstructured":"Kim, B., Xu, S., Savarese, S.: Accurate localization of 3D objects from RGB-D data using segmentation hypotheses. In: CVPR (2013)","DOI":"10.1109\/CVPR.2013.409"},{"issue":"3","key":"15_CR19","doi-asserted-by":"publisher","first-page":"302","DOI":"10.1007\/s11263-008-0202-0","volume":"82","author":"P Kohli","year":"2009","unstructured":"Kohli, P., Ladicky, L., Torr, P.H.S.: Robust higher order potentials for enforcing label consistency. IJCV 82(3), 302\u2013324 (2009)","journal-title":"IJCV"},{"key":"15_CR20","doi-asserted-by":"crossref","unstructured":"Kohli, P., Kumar, M.P.: Energy minimization for linear envelope MRFs. In: CVPR (2010)","DOI":"10.1109\/CVPR.2010.5539858"},{"key":"15_CR21","doi-asserted-by":"crossref","unstructured":"Komodakis, N., Paragios, N.: Beyond pairwise energies: efficient optimization for higher-order MRFs. In: CVPR (2009)","DOI":"10.1109\/CVPR.2009.5206846"},{"key":"15_CR22","unstructured":"Lee, D., Gupta, A., Hebert, M., Kanade, T.: Estimating spatial layout of rooms using volumetric reasoning about objects and surfaces. In: NIPS (2010)"},{"key":"15_CR23","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"478","DOI":"10.1007\/978-3-319-10599-4_31","volume-title":"Computer Vision \u2013 ECCV 2014","author":"JJ Lim","year":"2014","unstructured":"Lim, J.J., Khosla, A., Torralba, A.: FPM: fine pose parts-based model with 3D CAD models. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014, Part VI. LNCS, vol. 8694, pp. 478\u2013493. Springer, Heidelberg (2014)"},{"key":"15_CR24","doi-asserted-by":"crossref","unstructured":"Lim, J.J., Pirsiavash, H., Torralba, A.: Parsing IKEA objects: fne pose estimation. In: ICCV (2013)","DOI":"10.1109\/ICCV.2013.372"},{"key":"15_CR25","doi-asserted-by":"crossref","unstructured":"Lin, D., Fidler, S., Urtasun, R.: Holistic scene understanding for 3D object detection with RGB-D cameras. In: ICCV (2013)","DOI":"10.1109\/ICCV.2013.179"},{"key":"15_CR26","unstructured":"Mansinghka, V., Kulkarni, T., Perov, Y., Tenenbaum, J.: Approximate bayesian image interpretation using generative probabilistic graphics programs. In: NIPS 2013 (2013)"},{"key":"15_CR27","first-page":"1349","volume":"12","author":"JJ Mcauley","year":"2011","unstructured":"Mcauley, J.J., Caetano, T.S.: Faster algorithms for max-product message-passing. JMLR 12, 1349\u20131388 (2011)","journal-title":"JMLR"},{"key":"15_CR28","doi-asserted-by":"crossref","unstructured":"Menze, M., Geiger, A.: Object scene flow for autonomous vehicles. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298925"},{"key":"15_CR29","doi-asserted-by":"crossref","unstructured":"Menze, M., Heipke, C., Geiger, A.: Joint 3d estimation of vehicles and scene flow. In: ISA (2015)","DOI":"10.5194\/isprsannals-II-3-W5-427-2015"},{"key":"15_CR30","doi-asserted-by":"crossref","unstructured":"Newcombe, R.A., Izadi, S., Hilliges, O., Molyneaux, D., Kim, D., Davison, A.J., Kohli, P., Shotton, J., Hodges, S., Fitzgibbon, A.: Kinectfusion: real-time dense surface mapping and tracking. In: ISMAR (2011)","DOI":"10.1109\/ISMAR.2011.6092378"},{"issue":"1","key":"15_CR31","first-page":"39","volume":"112","author":"B Potetz","year":"2008","unstructured":"Potetz, B., Lee, T.S.: Efficient belief propagation for higher-order cliques using linear constraint nodes. CVIU 112(1), 39\u201354 (2008)","journal-title":"CVIU"},{"key":"15_CR32","unstructured":"Ren, X., Bo, L., Fox, D.: RGB-(D) scene labeling: features and algorithms. In: CVPR (2012)"},{"key":"15_CR33","unstructured":"Roberts, L.G.: Machine perception of three-dimensional solids. Ph.D. thesis, Massachusetts Institute of Technology (1963)"},{"key":"15_CR34","doi-asserted-by":"crossref","unstructured":"Rother, C., Kohli, P., Feng, W., Jia, J.: Minimizing sparse higher order energy functions of discrete variables. In: CVPR (2009)","DOI":"10.1109\/CVPR.2009.5206739"},{"key":"15_CR35","doi-asserted-by":"crossref","unstructured":"Satkin, S., Hebert, M.: 3DNN: viewpoint invariant 3D geometry matching for scene understanding. In: ICCV (2013)","DOI":"10.1109\/ICCV.2013.235"},{"key":"15_CR36","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"299","DOI":"10.1007\/978-3-642-33783-3_22","volume-title":"Computer Vision \u2013 ECCV 2012","author":"AG Schwing","year":"2012","unstructured":"Schwing, A.G., Urtasun, R.: Efficient exact inference for 3D indoor scene understanding. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012, Part VI. LNCS, vol. 7577, pp. 299\u2013313. Springer, Heidelberg (2012)"},{"key":"15_CR37","doi-asserted-by":"crossref","unstructured":"Schwing, A.G., Fidler, S., Pollefeys, M., Urtasun, R.: Box in the box: joint 3D layout and object reasoning from single images. In: ICCV (2013)","DOI":"10.1109\/ICCV.2013.51"},{"key":"15_CR38","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, Part V. LNCS, vol. 7576, pp. 746\u2013760. Springer, Heidelberg (2012)"},{"key":"15_CR39","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"634","DOI":"10.1007\/978-3-319-10599-4_41","volume-title":"Computer Vision \u2013 ECCV 2014","author":"S Song","year":"2014","unstructured":"Song, S., Xiao, J.: Sliding shapes for 3D object detection in depth images. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014, Part VI. LNCS, vol. 8694, pp. 634\u2013651. Springer, Heidelberg (2014)"},{"key":"15_CR40","unstructured":"Tarlow, D., Givoni, I.E., Zemel, R.S.: Hop-map: efficient message passing with high order potentials. In: AISTATS (2010)"},{"key":"15_CR41","doi-asserted-by":"crossref","unstructured":"Tighe, J., Niethammer, M., Lazebnik, S.: Scene parsing with object instances and occlusion ordering. In: CVPR (2014)","DOI":"10.1109\/CVPR.2014.479"},{"key":"15_CR42","doi-asserted-by":"crossref","unstructured":"Tsai, G., Xu, C., Liu, J., Kuipers, B.: Real-time indoor scene understanding using Bayesian filtering with motion cues. In: ICCV (2011)","DOI":"10.1109\/ICCV.2011.6126233"},{"issue":"11","key":"15_CR43","first-page":"1610","volume":"117","author":"C Wang","year":"2013","unstructured":"Wang, C., Komodakis, N., Paragios, N.: Markov random field modeling, inference & learning in computer vision & image understanding: a survey. CVIU 117(11), 1610\u20131627 (2013)","journal-title":"CVIU"},{"key":"15_CR44","doi-asserted-by":"crossref","unstructured":"Yamaguchi, K., McAllester, D., Urtasun, R.: Robust monocular epipolar flow estimation. In: CVPR (2013)","DOI":"10.1109\/CVPR.2013.243"},{"key":"15_CR45","doi-asserted-by":"crossref","unstructured":"Zhang, H., Geiger, A., Urtasun, R.: Understanding high-level semantics by modeling traffic patterns. In: ICCV (2013)","DOI":"10.1109\/ICCV.2013.379"},{"key":"15_CR46","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, Part VI. LNCS, vol. 8694, pp. 668\u2013686. Springer, Heidelberg (2014)"},{"key":"15_CR47","doi-asserted-by":"crossref","unstructured":"Zheng, B., Zhao, Y., Yu, J.C., Ikeuchi, K., Zhu, S.C.: Beyond point clouds: scene understanding by reasoning geometry and physics. In: CVPR (2013)","DOI":"10.1109\/CVPR.2013.402"},{"issue":"11","key":"15_CR48","doi-asserted-by":"publisher","first-page":"2608","DOI":"10.1109\/TPAMI.2013.87","volume":"35","author":"M Zia","year":"2013","unstructured":"Zia, M., Stark, M., Schiele, B., Schindler, K.: Detailed 3D representations for object recognition and modeling. PAMI 35(11), 2608\u20132623 (2013)","journal-title":"PAMI"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-24947-6_15","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,28]],"date-time":"2023-12-28T09:08:57Z","timestamp":1703754537000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-319-24947-6_15"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015]]},"ISBN":["9783319249469","9783319249476"],"references-count":48,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-24947-6_15","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2015]]},"assertion":[{"value":"3 November 2015","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}}]}}