{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T08:06:46Z","timestamp":1788941206748,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":66,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032370402","type":"print"},{"value":"9783032370419","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":[[2026]]},"DOI":"10.1007\/978-3-032-37041-9_2","type":"book-chapter","created":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T07:26:22Z","timestamp":1788938782000},"page":"21-39","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Video Generative Models as\u00a0Geometry Learner"],"prefix":"10.1007","author":[{"given":"Haosen","family":"Yang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jifei","family":"Song","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhensong","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiatian","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiankang","family":"Deng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,10]]},"reference":[{"key":"2_CR1","doi-asserted-by":"crossref","unstructured":"Aich, S., Vianney, J.M.U., Islam, M.A., Liu, M.K.B.: Bidirectional attention network for monocular depth estimation. In: 2021 IEEE International Conference on Robotics and Automation (ICRA), pp. 11746\u201311752. IEEE (2021)","DOI":"10.1109\/ICRA48506.2021.9560885"},{"key":"2_CR2","doi-asserted-by":"crossref","unstructured":"Bae, G., Budvytis, I., Cipolla, R.: Estimating and exploiting the aleatoric uncertainty in surface normal estimation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 13137\u201313146 (2021)","DOI":"10.1109\/ICCV48922.2021.01289"},{"key":"2_CR3","doi-asserted-by":"crossref","unstructured":"Bae, G., Davison, A.J.: Rethinking inductive biases for surface normal estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9535\u20139545 (2024)","DOI":"10.1109\/CVPR52733.2024.00911"},{"key":"2_CR4","unstructured":"Betker, J., et\u00a0al.: Improving image generation with better captions. Comput. Sci. 2(3), 8 (2023). https:\/\/cdn.openai.com\/papers\/dall-e-3.pdf"},{"key":"2_CR5","unstructured":"Bhat, S.F., Alhashim, I., Wonka, P.: AdaBins: depth estimation using adaptive bins. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4009\u20134018 (2021)"},{"key":"2_CR6","unstructured":"Blattmann, A., et al.: Stable video diffusion: scaling latent video diffusion models to large datasets. arXiv preprint arXiv:2311.15127 (2023)"},{"key":"2_CR7","doi-asserted-by":"crossref","unstructured":"Brooks, T., Holynski, A., Efros, A.A.: InstructPix2Pix: learning to follow image editing instructions. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18392\u201318402 (2023)","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"2_CR8","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":"2_CR9","unstructured":"Cabon, Y., Murray, N., Humenberger, M.: Virtual KITTI 2. arXiv preprint arXiv:2001.10773 (2020)"},{"key":"2_CR10","doi-asserted-by":"crossref","unstructured":"Chen, W., Qian, S., Fan, D., Kojima, N., Hamilton, M., Deng, J.: OASIS: a large-scale dataset for single image 3D in the wild. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 679\u2013688 (2020)","DOI":"10.1109\/CVPR42600.2020.00076"},{"key":"2_CR11","doi-asserted-by":"crossref","unstructured":"Dai, A., Chang, A.X., Savva, M., Halber, M., Funkhouser, T., Nie\u00dfner, M.: ScanNet: richly-annotated 3D reconstructions of indoor scenes. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5828\u20135839 (2017)","DOI":"10.1109\/CVPR.2017.261"},{"key":"2_CR12","doi-asserted-by":"publisher","unstructured":"Duan, Y., Guo, X., Zhu, Z.: DiffusionDepth: diffusion denoising approach for monocular depth estimation. In: Leonardis, A., Ricci, E., Roth, S., Russakovsky, O., Sattler, T., Varol, G. (eds.) Computer Vision, ECCV 2024. LNCS, vol. 15069, pp. 432\u2013449. Springer, Cham (2025). https:\/\/doi.org\/10.1007\/978-3-031-73247-8_25","DOI":"10.1007\/978-3-031-73247-8_25"},{"key":"2_CR13","doi-asserted-by":"crossref","unstructured":"Eftekhar, A., Sax, A., Malik, J., Zamir, A.: Omnidata: a scalable pipeline for making multi-task mid-level vision datasets from 3D scans. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10786\u201310796 (2021)","DOI":"10.1109\/ICCV48922.2021.01061"},{"key":"2_CR14","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, p. 27 (2014)"},{"key":"2_CR15","doi-asserted-by":"crossref","unstructured":"Fu, H., Gong, M., Wang, C., Batmanghelich, K., Tao, D.: Deep ordinal regression network for monocular depth estimation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2002\u20132011 (2018)","DOI":"10.1109\/CVPR.2018.00214"},{"key":"2_CR16","doi-asserted-by":"publisher","unstructured":"Fu, X., et al.: Geowizard: unleashing the diffusion priors for 3D geometry estimation from a single image. In: Leonardis, A., Ricci, E., Roth, S., Russakovsky, O., Sattler, T., Varol, G. (eds) Computer Vision, ECCV 2024. LNCS, vol. 15080, pp. 241\u2013258. Springer, Cham (2025). https:\/\/doi.org\/10.1007\/978-3-031-72670-5_14","DOI":"10.1007\/978-3-031-72670-5_14"},{"key":"2_CR17","doi-asserted-by":"crossref","unstructured":"Garcia, G.M., Abou Zeid, K., Schmidt, C., De Geus, D., Hermans, A., Leibe, B.: Fine-tuning image-conditional diffusion models is easier than you think. In: 2025 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV), pp. 753\u2013762. IEEE (2025)","DOI":"10.1109\/WACV61041.2025.00083"},{"issue":"11","key":"2_CR18","doi-asserted-by":"publisher","first-page":"1231","DOI":"10.1177\/0278364913491297","volume":"32","author":"A Geiger","year":"2013","unstructured":"Geiger, A., Lenz, P., Stiller, C., Urtasun, R.: Vision meets robotics: the KITTI dataset. Int. J. Robot. Res. 32(11), 1231\u20131237 (2013)","journal-title":"Int. J. Robot. Res."},{"key":"2_CR19","doi-asserted-by":"crossref","unstructured":"Godard, C., Mac Aodha, 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":"2_CR20","doi-asserted-by":"crossref","unstructured":"Gui, M., et al.: DepthFM: fast generative monocular depth estimation with flow matching. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 39, pp. 3203\u20133211 (2025)","DOI":"10.1609\/aaai.v39i3.32330"},{"key":"2_CR21","doi-asserted-by":"crossref","unstructured":"Guizilini, V., Vasiljevic, I., Chen, D., Ambru, R., Gaidon, A.: Towards zero-shot scale-aware monocular depth estimation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9233\u20139243 (2023)","DOI":"10.1109\/ICCV51070.2023.00847"},{"key":"2_CR22","unstructured":"He, J., et al.: Lotus: diffusion-based visual foundation model for high-quality dense prediction. arXiv preprint arXiv:2409.18124 (2024)"},{"key":"2_CR23","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."},{"key":"2_CR24","doi-asserted-by":"crossref","unstructured":"Hu, M., et al.: Metric3D v2: a versatile monocular geometric foundation model for zero-shot metric depth and surface normal estimation. IEEE Trans. Pattern Anal. Mach. Intell. (2024)","DOI":"10.1109\/TPAMI.2024.3444912"},{"key":"2_CR25","doi-asserted-by":"crossref","unstructured":"Hu, W., et al.: DepthCrafter: generating consistent long depth sequences for open-world videos. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 2005\u20132015 (2025)","DOI":"10.1109\/CVPR52734.2025.00193"},{"key":"2_CR26","doi-asserted-by":"crossref","unstructured":"Ji, Y., et al.: DDP: diffusion model for dense visual prediction. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 21741\u201321752 (2023)","DOI":"10.1109\/ICCV51070.2023.01987"},{"key":"2_CR27","doi-asserted-by":"crossref","unstructured":"Jiang, Z., Zheng, C., Laina, I., Larlus, D., Vedaldi, A.: Geo4D: leveraging video generators for geometric 4D scene reconstruction. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 20658\u201320671 (2025)","DOI":"10.1109\/ICCV51701.2025.01921"},{"key":"2_CR28","doi-asserted-by":"publisher","first-page":"26565","DOI":"10.52202\/068431-1926","volume":"35","author":"T Karras","year":"2022","unstructured":"Karras, T., Aittala, M., Aila, T., Laine, S.: Elucidating the design space of diffusion-based generative models. Adv. Neural. Inf. Process. Syst. 35, 26565\u201326577 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"2_CR29","doi-asserted-by":"crossref","unstructured":"Ke, B., Obukhov, A., Huang, S., Metzger, N., Daudt, R.C., Schindler, K.: Repurposing diffusion-based image generators for monocular depth estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9492\u20139502 (2024)","DOI":"10.1109\/CVPR52733.2024.00907"},{"key":"2_CR30","doi-asserted-by":"crossref","unstructured":"Kerbl, B., Kopanas, G., Leimk\u00fchler, T., Drettakis, G.: 3D gaussian splatting for real-time radiance field rendering. ACM Trans. Graph. 42(4), 139\u20131 (2023)","DOI":"10.1145\/3592433"},{"key":"2_CR31","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"331","DOI":"10.1007\/978-3-030-11015-4_25","volume-title":"Computer Vision \u2013 ECCV 2018 Workshops","author":"T Koch","year":"2019","unstructured":"Koch, T., Liebel, L., Fraundorfer, F., K\u00f6rner, M.: Evaluation of CNN-based single-image depth estimation methods. In: Leal-Taix\u00e9, L., Roth, S. (eds.) ECCV 2018. LNCS, vol. 11131, pp. 331\u2013348. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-11015-4_25"},{"key":"2_CR32","doi-asserted-by":"crossref","unstructured":"Krishnan, A., Yan, X., Casser, V., Kundu, A.: Orchid: image latent diffusion for joint appearance and geometry generation. arXiv preprint arXiv:2501.13087 (2025)","DOI":"10.1109\/ICCV51701.2025.02620"},{"key":"2_CR33","unstructured":"Lee, J.H., Han, M.K., Ko, D.W., Suh, I.H.: From big to small: multi-scale local planar guidance for monocular depth estimation. arXiv preprint arXiv:1907.10326 (2019)"},{"key":"2_CR34","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"},{"key":"2_CR35","doi-asserted-by":"crossref","unstructured":"Li, Z., Snavely, N.: MegaDepth: learning single-view depth prediction from internet photos. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2041\u20132050 (2018)","DOI":"10.1109\/CVPR.2018.00218"},{"issue":"6","key":"2_CR36","doi-asserted-by":"publisher","first-page":"837","DOI":"10.1007\/s11633-023-1458-0","volume":"20","author":"Z Li","year":"2023","unstructured":"Li, Z., Chen, Z., Liu, X., Jiang, J.: DepthFormer: exploiting long-range correlation and local information for accurate monocular depth estimation. Mach. Intell. Res. 20(6), 837\u2013854 (2023)","journal-title":"Mach. Intell. Res."},{"key":"2_CR37","doi-asserted-by":"publisher","unstructured":"Liu, H., et al.: PathoPainter: augmenting histopathology segmentation via tumor-aware inpainting. In: Gee, J.C., et al. (eds.) International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 408\u2013417. Springer, Cham (2025). https:\/\/doi.org\/10.1007\/978-3-032-05325-1_39","DOI":"10.1007\/978-3-032-05325-1_39"},{"key":"2_CR38","unstructured":"Poole, B., Jain, A., Barron, J.T., Mildenhall, B.: DreamFusion: text-to-3D using 2D diffusion. arXIv preprint arXiv:2209.14988 (2022)"},{"key":"2_CR39","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"2_CR40","doi-asserted-by":"crossref","unstructured":"Ranftl, R., Bochkovskiy, A., Koltun, V.: Vision transformers for dense prediction. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 12179\u201312188 (2021)","DOI":"10.1109\/ICCV48922.2021.01196"},{"issue":"3","key":"2_CR41","doi-asserted-by":"publisher","first-page":"1623","DOI":"10.1109\/TPAMI.2020.3019967","volume":"44","author":"R Ranftl","year":"2020","unstructured":"Ranftl, R., Lasinger, K., Hafner, D., Schindler, K., Koltun, V.: Towards robust monocular depth estimation: mixing datasets for zero-shot cross-dataset transfer. IEEE Trans. Pattern Anal. Mach. Intell. 44(3), 1623\u20131637 (2020)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"2_CR42","doi-asserted-by":"crossref","unstructured":"Roberts, M., et al.: Hypersim: a photorealistic synthetic dataset for holistic indoor scene understanding. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10912\u201310922 (2021)","DOI":"10.1109\/ICCV48922.2021.01073"},{"key":"2_CR43","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":"2_CR44","unstructured":"Salimans, T., Ho, J.: Progressive distillation for fast sampling of diffusion models. arXiv preprint arXiv:2202.00512 (2022)"},{"key":"2_CR45","doi-asserted-by":"publisher","first-page":"39443","DOI":"10.52202\/075280-1713","volume":"36","author":"S Saxena","year":"2023","unstructured":"Saxena, S., et al.: The surprising effectiveness of diffusion models for optical flow and monocular depth estimation. Adv. Neural. Inf. Process. Syst. 36, 39443\u201339469 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"2_CR46","unstructured":"Saxena, S., Kar, A., Norouzi, M., Fleet, D.J.: Monocular depth estimation using diffusion models. arXiv preprint arXiv:2302.14816 (2023)"},{"key":"2_CR47","doi-asserted-by":"crossref","unstructured":"Schops, T., et al.: A multi-view stereo benchmark with high-resolution images and multi-camera videos. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3260\u20133269 (2017)","DOI":"10.1109\/CVPR.2017.272"},{"key":"2_CR48","doi-asserted-by":"crossref","unstructured":"Shao, J., et al.: Learning temporally consistent video depth from video diffusion priors. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 22841\u201322852 (2025)","DOI":"10.1109\/CVPR52734.2025.02127"},{"key":"2_CR49","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"},{"key":"2_CR50","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":"2_CR51","unstructured":"Song, J., Meng, C., Ermon, S.: Denoising diffusion implicit models. arXiv preprint arXiv:2010.02502 (2020)"},{"key":"2_CR52","unstructured":"Sun, Y.T., et al.: UniGeo: taming video diffusion for unified consistent geometry estimation. arXiv preprint arXiv:2505.24521 (2025)"},{"key":"2_CR53","unstructured":"Vasiljevic, I., et al.: DIODE: a dense indoor and outdoor depth dataset. arXiv preprint arXiv:1908.00463 (2019)"},{"key":"2_CR54","unstructured":"Wan, T., et\u00a0al.: WAN: open and advanced large-scale video generative models. arXiv preprint arXiv:2503.20314 (2025)"},{"key":"2_CR55","unstructured":"Wang, P., et al.: SURGE: surface regularized geometry estimation from a single image. Adv. Neural. Inf. Process. Syst. 29 (2016)"},{"key":"2_CR56","doi-asserted-by":"crossref","unstructured":"Xu, D., Ouyang, W., Wang, X., Sebe, N.: PAD-Net: multi-tasks guided prediction-and-distillation network for simultaneous depth estimation and scene parsing. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 675\u2013684 (2018)","DOI":"10.1109\/CVPR.2018.00077"},{"key":"2_CR57","doi-asserted-by":"crossref","unstructured":"Yang, H., et al.: Fam diffusion: frequency and attention modulation for high-resolution image generation with stable diffusion. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 2459\u20132468 (2025)","DOI":"10.1109\/CVPR52734.2025.00235"},{"key":"2_CR58","doi-asserted-by":"crossref","unstructured":"Yang, H., et al.: Improving gaussian splatting with localized points management. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 21696\u201321705 (2025)","DOI":"10.1109\/CVPR52734.2025.02021"},{"key":"2_CR59","doi-asserted-by":"crossref","unstructured":"Yang, L., Kang, B., Huang, Z., Xu, X., Feng, J., Zhao, H.: Depth anything: unleashing the power of large-scale unlabeled data. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10371\u201310381 (2024)","DOI":"10.1109\/CVPR52733.2024.00987"},{"key":"2_CR60","doi-asserted-by":"publisher","first-page":"21875","DOI":"10.52202\/079017-0688","volume":"37","author":"L Yang","year":"2024","unstructured":"Yang, L., et al.: Depth Anything V2. Adv. Neural. Inf. Process. Syst. 37, 21875\u201321911 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"2_CR61","doi-asserted-by":"crossref","unstructured":"Yang, Z., Pan, Z., Yang, Y., Zhu, X., Zhang, L.: Driving scene synthesis on free-form trajectories with generative prior. arXiv preprint arXiv:2412.01717 (2024)","DOI":"10.1109\/ICCV51701.2025.02607"},{"issue":"6","key":"2_CR62","first-page":"1","volume":"43","author":"C Ye","year":"2024","unstructured":"Ye, C., et al.: StableNormal: reducing diffusion variance for stable and sharp normal. ACM Trans. Graph. (TOG) 43(6), 1\u201318 (2024)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"2_CR63","doi-asserted-by":"publisher","first-page":"25018","DOI":"10.52202\/068431-1814","volume":"35","author":"Z Yu","year":"2022","unstructured":"Yu, Z., Peng, S., Niemeyer, M., Sattler, T., Geiger, A.: MonoSDF: exploring monocular geometric cues for neural implicit surface reconstruction. Adv. Neural. Inf. Process. Syst. 35, 25018\u201325032 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"2_CR64","doi-asserted-by":"crossref","unstructured":"Yuan, W., Gu, X., Dai, Z., Zhu, S., Tan, P.: New CRFs: neural window fully-connected CRFs for monocular depth estimation. arXiv preprint arXiv:2203.01502 (2022)","DOI":"10.1109\/CVPR52688.2022.00389"},{"key":"2_CR65","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Cui, Z., Xu, C., Yan, Y., Sebe, N., Yang, J.: Pattern-affinitive propagation across depth, surface normal and semantic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4106\u20134115 (2019)","DOI":"10.1109\/CVPR.2019.00423"},{"key":"2_CR66","doi-asserted-by":"crossref","unstructured":"Zhao, W., Rao, Y., Liu, Z., Liu, B., Zhou, J., Lu, J.: Unleashing text-to-image diffusion models for visual perception. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 5729\u20135739 (2023)","DOI":"10.1109\/ICCV51070.2023.00527"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2026"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-37041-9_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T07:26:41Z","timestamp":1788938801000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37041-9_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032370402","9783032370419"],"references-count":66,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37041-9_2","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"10 September 2026","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":"Malm\u00f6","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Sweden","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 September 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 September 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}