{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,28]],"date-time":"2025-03-28T00:59:56Z","timestamp":1743123596172,"version":"3.40.3"},"publisher-location":"Cham","reference-count":43,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031726545"},{"type":"electronic","value":"9783031726552"}],"license":[{"start":{"date-parts":[[2024,12,6]],"date-time":"2024-12-06T00:00:00Z","timestamp":1733443200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,6]],"date-time":"2024-12-06T00:00:00Z","timestamp":1733443200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-3-031-72655-2_3","type":"book-chapter","created":{"date-parts":[[2024,12,5]],"date-time":"2024-12-05T10:12:10Z","timestamp":1733393530000},"page":"37-53","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["SEDiff: Structure Extraction for\u00a0Domain Adaptive Depth Estimation via\u00a0Denoising Diffusion Models"],"prefix":"10.1007","author":[{"given":"Dongseok","family":"Shim","sequence":"first","affiliation":[]},{"given":"H. Jin","family":"Kim","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,12,6]]},"reference":[{"key":"3_CR1","doi-asserted-by":"crossref","unstructured":"Avrahami, O., Lischinski, D., Fried, O.: Blended diffusion for text-driven editing of natural images. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18208\u201318218 (2022)","DOI":"10.1109\/CVPR52688.2022.01767"},{"key":"3_CR2","doi-asserted-by":"crossref","unstructured":"Chen, X., Wang, Y., Chen, X., Zeng, W.: S2R-DepthNet: learning a generalizable depth-specific structural representation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3034\u20133043 (2021)","DOI":"10.1109\/CVPR46437.2021.00305"},{"key":"3_CR3","unstructured":"Couprie, C., Farabet, C., Najman, L., LeCun, Y.: Indoor semantic segmentation using depth information. arXiv preprint arXiv:1301.3572 (2013)"},{"key":"3_CR4","first-page":"8780","volume":"34","author":"P Dhariwal","year":"2021","unstructured":"Dhariwal, P., Nichol, A.: Diffusion models beat gans on image synthesis. Adv. Neural Inf. Process. Syst. 34, 8780\u20138794 (2021)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"3_CR5","unstructured":"Eigen, D., Puhrsch, C., Fergus, R.: Depth map prediction from a single image using a multi-scale deep network. Adv. Neural Inf. Process. Syst. 27 (2014)"},{"key":"3_CR6","doi-asserted-by":"crossref","unstructured":"Gaidon, A., Wang, Q., Cabon, Y., Vig, E.: Virtual worlds as proxy for multi-object tracking analysis. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4340\u20134349 (2016)","DOI":"10.1109\/CVPR.2016.470"},{"key":"3_CR7","doi-asserted-by":"crossref","unstructured":"Geiger, A., Lenz, P., Urtasun, R.: Are we ready for autonomous driving? The kitti vision benchmark suite. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition, pp. 3354\u20133361. IEEE (2012)","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"3_CR8","doi-asserted-by":"crossref","unstructured":"Godard, C., Mac\u00a0Aodha, O., Brostow, G.J.: Unsupervised monocular depth estimation with left-right consistency. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 270\u2013279 (2017)","DOI":"10.1109\/CVPR.2017.699"},{"key":"3_CR9","doi-asserted-by":"crossref","unstructured":"Gonzalez, R.C.: Digital Image Processing. Pearson education, India (2009)","DOI":"10.1117\/1.3115362"},{"key":"3_CR10","unstructured":"Goodfellow, I., et al.: Generative adversarial nets. Adv. Neural Inf. Process. Syst. 27 (2014)"},{"key":"3_CR11","doi-asserted-by":"crossref","unstructured":"Gu, S., et al.: Vector quantized diffusion model for text-to-image synthesis. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10696\u201310706 (2022)","DOI":"10.1109\/CVPR52688.2022.01043"},{"key":"3_CR12","doi-asserted-by":"crossref","unstructured":"Guizilini, V., Ambrus, R., Pillai, S., Raventos, A., Gaidon, A.: 3D packing for self-supervised monocular depth estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2485\u20132494 (2020)","DOI":"10.1109\/CVPR42600.2020.00256"},{"key":"3_CR13","first-page":"6840","volume":"33","author":"J Ho","year":"2020","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. Adv. Neural Inf. Process. Syst. 33, 6840\u20136851 (2020)","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"1","key":"3_CR14","first-page":"2249","volume":"23","author":"J Ho","year":"2022","unstructured":"Ho, J., Saharia, C., Chan, W., Fleet, D.J., Norouzi, M., Salimans, T.: Cascaded diffusion models for high fidelity image generation. J. Mach. Learn. Res. 23(1), 2249\u20132281 (2022)","journal-title":"J. Mach. Learn. Res."},{"key":"3_CR15","doi-asserted-by":"crossref","unstructured":"Huang, X., Belongie, S.: Arbitrary style transfer in real-time with adaptive instance normalization. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1501\u20131510 (2017)","DOI":"10.1109\/ICCV.2017.167"},{"key":"3_CR16","doi-asserted-by":"crossref","unstructured":"Isola, P., Zhu, J.Y., Zhou, T., Efros, A.A.: Image-to-image translation with conditional adversarial networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1125\u20131134 (2017)","DOI":"10.1109\/CVPR.2017.632"},{"key":"3_CR17","unstructured":"Nichol, W.K.: Painter by numbers (2016). https:\/\/kaggle.com\/competitions\/painter-by-numbers"},{"key":"3_CR18","unstructured":"Kingma, D.P., Welling, M.: Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114 (2013)"},{"key":"3_CR19","doi-asserted-by":"crossref","unstructured":"Kundu, J.N., Uppala, P.K., Pahuja, A., Babu, R.V.: Adadepth: unsupervised content congruent adaptation for depth estimation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2656\u20132665 (2018)","DOI":"10.1109\/CVPR.2018.00281"},{"key":"3_CR20","unstructured":"Lang, B.: The Concept of Style. Cornell University Press, Ithaca (1987)"},{"key":"3_CR21","doi-asserted-by":"crossref","unstructured":"Li, B., Shen, C., Dai, Y., Van Den\u00a0Hengel, 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":"3","key":"3_CR22","doi-asserted-by":"publisher","first-page":"752","DOI":"10.1007\/s11263-022-01718-1","volume":"131","author":"A Lopez-Rodriguez","year":"2023","unstructured":"Lopez-Rodriguez, A., Mikolajczyk, K.: DESC: domain adaptation for depth estimation via semantic consistency. Int. J. Comput. Vis. 131(3), 752\u2013771 (2023)","journal-title":"Int. J. Comput. Vis."},{"key":"3_CR23","doi-asserted-by":"crossref","unstructured":"Lugmayr, A., Danelljan, M., Romero, A., Yu, F., Timofte, R., Van\u00a0Gool, L.: Repaint: inpainting using denoising diffusion probabilistic models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11461\u201311471 (2022)","DOI":"10.1109\/CVPR52688.2022.01117"},{"key":"3_CR24","unstructured":"Meng, C., et al.: Sdedit: guided image synthesis and editing with stochastic differential equations. In: International Conference on Learning Representations (2021)"},{"key":"3_CR25","doi-asserted-by":"crossref","unstructured":"M\u00fcller, N., Siddiqui, Y., Porzi, L., Bulo, S.R., Kontschieder, P., Nie\u00dfner, M.: Diffrf: rendering-guided 3d radiance field diffusion. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4328\u20134338 (2023)","DOI":"10.1109\/CVPR52729.2023.00421"},{"key":"3_CR26","unstructured":"Nichol, A.Q., et al.: Glide: towards photorealistic image generation and editing with text-guided diffusion models. In: International Conference on Machine Learning, pp. 16784\u201316804. PMLR (2022)"},{"key":"3_CR27","unstructured":"PNVR, K., Zhou, H., Jacobs, D.: Sharingan: combining synthetic and real data for unsupervised geometry estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13974\u201313983 (2020)"},{"key":"3_CR28","unstructured":"Poole, B., Jain, A., Barron, J.T., Mildenhall, B.: Dreamfusion: text-to-3d using 2d diffusion. In: The Eleventh International Conference on Learning Representations (2022)"},{"key":"3_CR29","unstructured":"Rezende, D., Mohamed, S.: Variational inference with normalizing flows. In: International Conference on Machine Learning, pp. 1530\u20131538. PMLR (2015)"},{"key":"3_CR30","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10684\u201310695 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"3_CR31","first-page":"36479","volume":"35","author":"C Saharia","year":"2022","unstructured":"Saharia, C., et al.: Photorealistic text-to-image diffusion models with deep language understanding. Adv. Neural Inf. Process. Syst. 35, 36479\u201336494 (2022)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"3_CR32","unstructured":"Seo, J., et al.: Let 2D diffusion model know 3d-consistency for robust text-to-3d generation. In: International Conference on Learning Representations (2024)"},{"key":"3_CR33","unstructured":"Sohl-Dickstein, J., Weiss, E., Maheswaranathan, N., Ganguli, S.: Deep unsupervised learning using nonequilibrium thermodynamics. In: International Conference on Machine Learning, pp. 2256\u20132265. PMLR (2015)"},{"key":"3_CR34","unstructured":"Song, J., Meng, C., Ermon, S.: Denoising diffusion implicit models. In: International Conference on Learning Representations (2020)"},{"key":"3_CR35","unstructured":"Straub, J., et\u00a0al.: The replica dataset: a digital replica of indoor spaces. arXiv preprint arXiv:1906.05797 (2019)"},{"key":"3_CR36","doi-asserted-by":"crossref","unstructured":"Wang, Z., Zhao, L., Xing, W.: Stylediffusion: controllable disentangled style transfer via diffusion models. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 7677\u20137689 (2023)","DOI":"10.1109\/ICCV51070.2023.00706"},{"key":"3_CR37","doi-asserted-by":"crossref","unstructured":"Xie, S., Zhang, Z., Lin, Z., Hinz, T., Zhang, K.: SmartBrush: text and shape guided object inpainting with diffusion model. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 22428\u201322437 (2023)","DOI":"10.1109\/CVPR52729.2023.02148"},{"key":"3_CR38","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 the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5354\u20135362 (2017)","DOI":"10.1109\/CVPR.2017.25"},{"key":"3_CR39","doi-asserted-by":"crossref","unstructured":"Yang, G., Song, X., Huang, C., Deng, Z., Shi, J., Zhou, B.: Drivingstereo: a large-scale dataset for stereo matching in autonomous driving scenarios. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 899\u2013908 (2019)","DOI":"10.1109\/CVPR.2019.00099"},{"key":"3_CR40","doi-asserted-by":"publisher","unstructured":"Yen, Y.T., Lu, C.N., Chiu, W.C., Tsai, Y.H.: 3D-PL: domain adaptive depth estimation with 3D-aware pseudo-labeling. In: Avidan, S., Brostow, G., Cisse, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision \u2013 ECCV 2022. ECCV 2022. LNCS, vol. 13687, pp. 710\u2013728. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19812-0_41","DOI":"10.1007\/978-3-031-19812-0_41"},{"key":"3_CR41","doi-asserted-by":"crossref","unstructured":"Zhang, R., Isola, P., Efros, A.A., Shechtman, E., Wang, O.: The unreasonable effectiveness of deep features as a perceptual metric. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 586\u2013595 (2018)","DOI":"10.1109\/CVPR.2018.00068"},{"key":"3_CR42","doi-asserted-by":"crossref","unstructured":"Zhao, S., Fu, H., Gong, M., Tao, D.: Geometry-aware symmetric domain adaptation for monocular depth estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9788\u20139798 (2019)","DOI":"10.1109\/CVPR.2019.01002"},{"key":"3_CR43","doi-asserted-by":"crossref","unstructured":"Zheng, C., Cham, T.J., Cai, J.: T2net: synthetic-to-realistic translation for solving single-image depth estimation tasks. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 767\u2013783 (2018)","DOI":"10.1007\/978-3-030-01234-2_47"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-72655-2_3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,5]],"date-time":"2024-12-05T11:25:56Z","timestamp":1733397956000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72655-2_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,6]]},"ISBN":["9783031726545","9783031726552"],"references-count":43,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72655-2_3","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,12,6]]},"assertion":[{"value":"6 December 2024","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":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}