{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,19]],"date-time":"2026-02-19T17:07:08Z","timestamp":1771520828434,"version":"3.50.1"},"publisher-location":"Cham","reference-count":62,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030012632","type":"print"},{"value":"9783030012649","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\/978-3-030-01264-9_13","type":"book-chapter","created":{"date-parts":[[2018,10,8]],"date-time":"2018-10-08T08:20:53Z","timestamp":1538986853000},"page":"211-229","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":45,"title":["Single Image Intrinsic Decomposition Without a Single Intrinsic Image"],"prefix":"10.1007","author":[{"given":"Wei-Chiu","family":"Ma","sequence":"first","affiliation":[]},{"given":"Hang","family":"Chu","sequence":"additional","affiliation":[]},{"given":"Bolei","family":"Zhou","sequence":"additional","affiliation":[]},{"given":"Raquel","family":"Urtasun","sequence":"additional","affiliation":[]},{"given":"Antonio","family":"Torralba","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2018,10,9]]},"reference":[{"key":"13_CR1","doi-asserted-by":"crossref","unstructured":"Adelson, E.H., Pentland, A.P.: The perception of shading and reflectance. In: Perception as Bayesian Inference. Cambridge University Press, New York (1996)","DOI":"10.1017\/CBO9780511984037.014"},{"key":"13_CR2","doi-asserted-by":"crossref","unstructured":"Barron, J.T., Malik, J.: Intrinsic scene properties from a single RGB-D image. In: CVPR (2013)","DOI":"10.1109\/CVPR.2013.10"},{"key":"13_CR3","doi-asserted-by":"crossref","unstructured":"Barron, J.T., Malik, J.: Shape, illumination, and reflectance from shading. In: PAMI (2015)","DOI":"10.1109\/TPAMI.2014.2377712"},{"key":"13_CR4","first-page":"3","volume":"2","author":"H Barrow","year":"1978","unstructured":"Barrow, H., Tenenbaum, J.: Recovering intrinsic scene characteristics from images. Comput. Vis. Syst. 2, 3\u201326 (1978)","journal-title":"Comput. Vis. Syst."},{"key":"13_CR5","unstructured":"Bell, M., Freeman, E.: Learning local evidence for shading and reflectance. In: ICCV (2001)"},{"issue":"4","key":"13_CR6","doi-asserted-by":"publisher","first-page":"159","DOI":"10.1145\/2601097.2601206","volume":"33","author":"S Bell","year":"2014","unstructured":"Bell, S., Bala, K., Snavely, N.: Intrinsic images in the wild. TOG 33(4), 159 (2014)","journal-title":"TOG"},{"issue":"6","key":"13_CR7","doi-asserted-by":"publisher","first-page":"197","DOI":"10.1145\/2661229.2661253","volume":"33","author":"N Bonneel","year":"2014","unstructured":"Bonneel, N., Sunkavalli, K., Tompkin, J., Sun, D., Paris, S., Pfister, H.: Interactive intrinsic video editing. TOG 33(6), 197 (2014)","journal-title":"TOG"},{"issue":"5","key":"13_CR8","doi-asserted-by":"publisher","first-page":"130","DOI":"10.1145\/1618452.1618476","volume":"28","author":"A Bousseau","year":"2009","unstructured":"Bousseau, A., Paris, S., Durand, F.: User-assisted intrinsic images. TOG 28(5), 130 (2009)","journal-title":"TOG"},{"key":"13_CR9","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"611","DOI":"10.1007\/978-3-642-33783-3_44","volume-title":"Computer Vision \u2013 ECCV 2012","author":"DJ Butler","year":"2012","unstructured":"Butler, D.J., Wulff, J., Stanley, G.B., Black, M.J.: A naturalistic open source movie for optical flow evaluation. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012. LNCS, vol. 7577, pp. 611\u2013625. Springer, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-33783-3_44"},{"key":"13_CR10","unstructured":"Chang, A.X., et al.: ShapeNet: an information-rich 3D model repository. arXiv (2015)"},{"key":"13_CR11","doi-asserted-by":"crossref","unstructured":"Chen, Q., Koltun, V.: A simple model for intrinsic image decomposition with depth cues. In: ICCV (2013)","DOI":"10.1109\/ICCV.2013.37"},{"key":"13_CR12","unstructured":"Chen, W., Fu, Z., Yang, D., Deng, J.: Single-image depth perception in the wild. In: NIPS (2016)"},{"key":"13_CR13","unstructured":"Eigen, D., Puhrsch, C., Fergus, R.: Depth map prediction from a single image using a multi-scale deep network. In: NIPS (2014)"},{"key":"13_CR14","doi-asserted-by":"crossref","unstructured":"Finlayson, G.D., Hordley, S.D., Drew, M.S.: Removing shadows from images using retinex. In: Color and Imaging Conference (2002)","DOI":"10.1007\/3-540-47979-1_55"},{"key":"13_CR15","doi-asserted-by":"crossref","unstructured":"Godard, C., Mac Aodha, O., Brostow, G.J.: Unsupervised monocular depth estimation with left-right consistency. In: CVPR (2016)","DOI":"10.1109\/CVPR.2017.699"},{"key":"13_CR16","doi-asserted-by":"crossref","unstructured":"Grosse, R., Johnson, M.K., Adelson, E.H., Freeman, W.T.: Ground truth dataset and baseline evaluations for intrinsic image algorithms. In: ICCV (2009)","DOI":"10.1109\/ICCV.2009.5459428"},{"key":"13_CR17","doi-asserted-by":"crossref","unstructured":"Hauagge, D., Wehrwein, S., Bala, K., Snavely, N.: Photometric ambient occlusion. In: CVPR (2013)","DOI":"10.1109\/CVPR.2013.325"},{"key":"13_CR18","doi-asserted-by":"crossref","unstructured":"Hauagge, D.C., Wehrwein, S., Upchurch, P., Bala, K., Snavely, N.: Reasoning about photo collections using models of outdoor illumination. In: BMVC (2014)","DOI":"10.5244\/C.28.78"},{"key":"13_CR19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-662-09771-7","volume-title":"Robot Vision","author":"B Horn","year":"1986","unstructured":"Horn, B.: Robot Vision. Springer, Heidelberg (1986). https:\/\/doi.org\/10.1007\/978-3-662-09771-7"},{"key":"13_CR20","doi-asserted-by":"crossref","unstructured":"Hui, Z., Sankaranarayanan, A.C., Sunkavalli, K., Hadap, S.: White balance under mixed illumination using flash photography. In: ICCP (2016)","DOI":"10.1109\/ICCPHOT.2016.7492879"},{"key":"13_CR21","unstructured":"Janner, M., Wu, J., Kulkarni, T.D., Yildirim, I., Tenenbaum, J.: Self-supervised intrinsic image decomposition. In: NIPS (2017)"},{"key":"13_CR22","doi-asserted-by":"crossref","unstructured":"Jayaraman, D., Grauman, K.: Learning image representations tied to ego-motion. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.166"},{"key":"13_CR23","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"218","DOI":"10.1007\/978-3-319-10584-0_15","volume-title":"Computer Vision \u2013 ECCV 2014","author":"J Jeon","year":"2014","unstructured":"Jeon, J., Cho, S., Tong, X., Lee, S.: Intrinsic image decomposition using structure-texture separation and surface normals. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8695, pp. 218\u2013233. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10584-0_15"},{"issue":"6","key":"13_CR24","doi-asserted-by":"publisher","first-page":"157","DOI":"10.1145\/2070781.2024191","volume":"30","author":"K Karsch","year":"2011","unstructured":"Karsch, K., Hedau, V., Forsyth, D., Hoiem, D.: Rendering synthetic objects into legacy photographs. TOG 30(6), 157 (2011)","journal-title":"TOG"},{"key":"13_CR25","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"143","DOI":"10.1007\/978-3-319-46484-8_9","volume-title":"Computer Vision \u2013 ECCV 2016","author":"S Kim","year":"2016","unstructured":"Kim, S., Park, K., Sohn, K., Lin, S.: Unified depth prediction and intrinsic image decomposition from a single image via joint convolutional neural fields. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9912, pp. 143\u2013159. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46484-8_9"},{"key":"13_CR26","unstructured":"Kingma, D., Ba, J.: Adam: a method for stochastic optimization. arXiv (2014)"},{"key":"13_CR27","doi-asserted-by":"crossref","unstructured":"Kong, N., Black, M.J.: Intrinsic depth: improving depth transfer with intrinsic images. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.401"},{"key":"13_CR28","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"360","DOI":"10.1007\/978-3-319-10605-2_24","volume-title":"Computer Vision \u2013 ECCV 2014","author":"N Kong","year":"2014","unstructured":"Kong, N., Gehler, P.V., Black, M.J.: Intrinsic video. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8690, pp. 360\u2013375. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10605-2_24"},{"key":"13_CR29","doi-asserted-by":"crossref","unstructured":"Laffont, P.Y., Bazin, J.C.: Intrinsic decomposition of image sequences from local temporal variations. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.57"},{"key":"13_CR30","doi-asserted-by":"crossref","unstructured":"Laffont, P.Y., Bousseau, A., Drettakis, G.: Rich intrinsic image decomposition of outdoor scenes from multiple views. In: TVCG (2013)","DOI":"10.1145\/2343045.2343113"},{"issue":"1","key":"13_CR31","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1364\/JOSA.61.000001","volume":"61","author":"EH Land","year":"1971","unstructured":"Land, E.H., McCann, J.J.: Lightness and retinex theory. J. Opt. Soc. Am. 61(1), 1\u201311 (1971)","journal-title":"J. Opt. Soc. Am."},{"key":"13_CR32","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"577","DOI":"10.1007\/978-3-319-46493-0_35","volume-title":"Computer Vision \u2013 ECCV 2016","author":"G Larsson","year":"2016","unstructured":"Larsson, G., Maire, M., Shakhnarovich, G.: Learning representations for automatic colorization. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9908, pp. 577\u2013593. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46493-0_35"},{"key":"13_CR33","doi-asserted-by":"crossref","unstructured":"Li, Z., Snavely, N.: Learning intrinsic image decomposition from watching the world. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00942"},{"key":"13_CR34","unstructured":"Liu, X., Jiang, L., Wong, T.T., Fu, C.W.: Statistical invariance for texture synthesis. In: TVCG (2012)"},{"key":"13_CR35","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"13_CR36","doi-asserted-by":"crossref","unstructured":"Matsushita, Y., Nishino, K., Ikeuchi, K., Sakauchi, M.: Illumination normalization with time-dependent intrinsic images for video surveillance. In: PAMI (2004)","DOI":"10.1109\/TPAMI.2004.86"},{"key":"13_CR37","doi-asserted-by":"crossref","unstructured":"Meka, A., Maximov, M., Zollh\u00f6fer, M., Chatterjee, A., Richardt, C., Theobalt, C.: Live intrinsic material estimation. arXiv (2018)","DOI":"10.1109\/CVPR.2018.00661"},{"issue":"4","key":"13_CR38","doi-asserted-by":"publisher","first-page":"109","DOI":"10.1145\/2897824.2925907","volume":"35","author":"A Meka","year":"2016","unstructured":"Meka, A., Zollh\u00f6fer, M., Richardt, C., Theobalt, C.: Live intrinsic video. TOG 35(4), 109 (2016)","journal-title":"TOG"},{"key":"13_CR39","doi-asserted-by":"crossref","unstructured":"Narihira, T., Maire, M., Yu, S.X.: Direct intrinsics: learning Albedo-shading decomposition by convolutional regression. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.342"},{"key":"13_CR40","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"483","DOI":"10.1007\/978-3-319-46484-8_29","volume-title":"Computer Vision \u2013 ECCV 2016","author":"A Newell","year":"2016","unstructured":"Newell, A., Yang, K., Deng, J.: Stacked hourglass networks for human pose estimation. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9912, pp. 483\u2013499. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46484-8_29"},{"key":"13_CR41","doi-asserted-by":"crossref","unstructured":"Oh, B.M., Chen, M., Dorsey, J., Durand, F.: Image-based modeling and photo editing. In: Computer Graphics and Interactive Techniques (2001)","DOI":"10.1145\/383259.383310"},{"key":"13_CR42","unstructured":"Omer, I., Werman, M.: Color lines: image specific color representation. In: CVPR (2004)"},{"key":"13_CR43","doi-asserted-by":"crossref","unstructured":"Pathak, D., Krahenbuhl, P., Donahue, J., Darrell, T., Efros, A.A.: Context encoders: feature learning by inpainting. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.278"},{"key":"13_CR44","unstructured":"Rezende, D.J., Eslami, S.A., Mohamed, S., Battaglia, P., Jaderberg, M., Heess, N.: Unsupervised learning of 3D structure from images. In: NIPS (2016)"},{"key":"13_CR45","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: U-net: convolutional networks for biomedical image segmentation. In: MIC-CAI (2015)","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"13_CR46","unstructured":"Rother, C., Kiefel, M., Zhang, L., Sch\u00f6lkopf, B., Gehler, P.V.: Recovering intrinsic images with a global sparsity prior on reflectance. In: NIPS (2011)"},{"key":"13_CR47","doi-asserted-by":"crossref","unstructured":"Shen, J., Yang, X., Jia, Y., Li, X.: Intrinsic images using optimization. In: CVPR (2011)","DOI":"10.1109\/CVPR.2011.5995507"},{"key":"13_CR48","doi-asserted-by":"crossref","unstructured":"Shi, J., Dong, Y., Su, H., Yu, S.X.: Learning non-lambertian object intrinsics across shapenet categories (2017)","DOI":"10.1109\/CVPR.2017.619"},{"key":"13_CR49","doi-asserted-by":"crossref","unstructured":"Shu, Z., Yumer, E., Hadap, S., Sunkavalli, K., Shechtman, E., Samaras, D.: Neural face editing with intrinsic image disentangling. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.578"},{"key":"13_CR50","unstructured":"Tappen, M.F., Freeman, W.T., Adelson, E.H.: Recovering intrinsic images from a single image. In: NIPS (2003)"},{"key":"13_CR51","unstructured":"Tung, H.Y., Tung, H.W., Yumer, E., Fragkiadaki, K.: Self-supervised learning of motion capture. In: NIPS (2017)"},{"key":"13_CR52","doi-asserted-by":"crossref","unstructured":"Tung, H.Y.F., Harley, A.W., Seto, W., Fragkiadaki, K.: Adversarial inverse graphics networks: learning 2D-to-3D lifting and image-to-image translation from unpaired supervision. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.467"},{"key":"13_CR53","unstructured":"Vijayanarasimhan, S., Ricco, S., Schmid, C., Sukthankar, R., Fragkiadaki, K.: SFM-Net: learning of structure and motion from video. arXiv (2017)"},{"key":"13_CR54","doi-asserted-by":"crossref","unstructured":"Wang, X., Gupta, A.: Unsupervised learning of visual representations using videos. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.320"},{"key":"13_CR55","unstructured":"Weiss, Y.: Deriving intrinsic images from image sequences. In: ICCV (2001)"},{"key":"13_CR56","unstructured":"Yan, X., Yang, J., Yumer, E., Guo, Y., Lee, H.: Perspective transformer nets: learning single-view 3D object reconstruction without 3D supervision. In: NIPS (2016)"},{"key":"13_CR57","unstructured":"Yang, J., Reed, S.E., Yang, M.H., Lee, H.: Weakly-supervised disentangling with recurrent transformations for 3D view synthesis. In: NIPS (2015)"},{"key":"13_CR58","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"649","DOI":"10.1007\/978-3-319-46487-9_40","volume-title":"Computer Vision \u2013 ECCV 2016","author":"R Zhang","year":"2016","unstructured":"Zhang, R., Isola, P., Efros, A.A.: Colorful image colorization. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9907, pp. 649\u2013666. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46487-9_40"},{"key":"13_CR59","doi-asserted-by":"crossref","unstructured":"Zhao, H., Gan, C., Rouditchenko, A., Vondrick, C., McDermott, J., Torralba, A.: The sound of pixels. arXiv (2018)","DOI":"10.1007\/978-3-030-01246-5_35"},{"key":"13_CR60","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 (2017)","DOI":"10.1109\/CVPR.2017.700"},{"key":"13_CR61","doi-asserted-by":"crossref","unstructured":"Zhou, T., Krahenbuhl, P., Efros, A.A.: Learning data-driven reflectance priors for intrinsic image decomposition. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.396"},{"key":"13_CR62","doi-asserted-by":"crossref","unstructured":"Zoran, D., Isola, P., Krishnan, D., Freeman, W.T.: Learning ordinal relationships for mid-level vision. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.52"}],"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\/978-3-030-01264-9_13","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,8]],"date-time":"2022-10-08T00:50:24Z","timestamp":1665190224000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-01264-9_13"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783030012632","9783030012649"],"references-count":62,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-01264-9_13","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":"9 October 2018","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}