{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,12]],"date-time":"2025-07-12T01:25:42Z","timestamp":1752283542713,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":31,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819785070"},{"type":"electronic","value":"9789819785087"}],"license":[{"start":{"date-parts":[[2024,11,3]],"date-time":"2024-11-03T00:00:00Z","timestamp":1730592000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,3]],"date-time":"2024-11-03T00:00:00Z","timestamp":1730592000000},"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\/978-981-97-8508-7_23","type":"book-chapter","created":{"date-parts":[[2024,11,2]],"date-time":"2024-11-02T06:10:04Z","timestamp":1730527804000},"page":"328-342","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Discriminative-Guided Diffusion-Based Self-supervised Monocular Depth Estimation"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-4673-2088","authenticated-orcid":false,"given":"Runze","family":"Liu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0432-7329","authenticated-orcid":false,"given":"Guanghui","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1579-3942","authenticated-orcid":false,"given":"Dongchen","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-6655-188X","authenticated-orcid":false,"given":"Lei","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3307-9838","authenticated-orcid":false,"given":"Xiaolin","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7478-4544","authenticated-orcid":false,"given":"Jiamao","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,11,3]]},"reference":[{"key":"23_CR1","doi-asserted-by":"crossref","unstructured":"Zhou, T., et al.: Unsupervised learning of depth and ego-motion from video. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2017)","DOI":"10.1109\/CVPR.2017.700"},{"key":"23_CR2","unstructured":"Bian, J., et al.: Unsupervised scale-consistent depth and ego-motion learning from monocular video. Adv. Neural Inform. Process. Syst. 32 (2019)"},{"key":"23_CR3","doi-asserted-by":"crossref","unstructured":"Godard, C., et al. Digging into self-supervised monocular depth estimation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (2019)","DOI":"10.1109\/ICCV.2019.00393"},{"key":"23_CR4","doi-asserted-by":"crossref","unstructured":"Bian, J.-W., et al.: Unsupervised scale-consistent depth learning from video. Int. J. Comput. Vis. 129(9), 2548\u20142564 (2021)","DOI":"10.1007\/s11263-021-01484-6"},{"key":"23_CR5","unstructured":"Goodfellow, I., et al.: Generative adversarial nets. Adv. Neural Inform. Process. Syst. 27 (2014)"},{"key":"23_CR6","doi-asserted-by":"crossref","unstructured":"Almalioglu, Y., et al.: GANVO: unsupervised deep monocular visual odometry and depth estimation with generative adversarial networks. In: 2019 International Conference on Robotics and Automation (ICRA). IEEE (2019)","DOI":"10.1109\/ICRA.2019.8793512"},{"key":"23_CR7","doi-asserted-by":"crossref","unstructured":"Li, S., et al.: Sequential adversarial learning for self-supervised deep visual odometry. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (2019)","DOI":"10.1109\/ICCV.2019.00294"},{"key":"23_CR8","doi-asserted-by":"crossref","unstructured":"Zhao, C., et al.: Masked GAN for unsupervised depth and pose prediction with scale consistency. IEEE Trans. Neural Netw. Learn. Syst. 32(12), 5392\u20135403 (2020)","DOI":"10.1109\/TNNLS.2020.3044181"},{"key":"23_CR9","doi-asserted-by":"crossref","unstructured":"Kaneko, T., Harada, T.: Noise robust generative adversarial networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2020)","DOI":"10.1109\/CVPR42600.2020.00843"},{"key":"23_CR10","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":"23_CR11","unstructured":"Song, C., Stefano: Denoising diffusion implicit models. In: International Conference on Learning Representations (2021)"},{"key":"23_CR12","unstructured":"Saxena, S., et al.: Monocular depth estimation using diffusion models (2023). arXiv preprint arXiv:2302.14816"},{"key":"23_CR13","doi-asserted-by":"crossref","unstructured":"Duan, Y., Guo, X., Zhu, Z.: Diffusiondepth: diffusion denoising approach for monocular depth estimation (2023). arXiv preprint arXiv:2303.05021","DOI":"10.1007\/978-3-031-73247-8_25"},{"key":"23_CR14","doi-asserted-by":"crossref","unstructured":"Chawla, H., et al.: Image masking for robust self-supervised monocular depth estimation. In: 2023 IEEE International Conference on Robotics and Automation (ICRA). IEEE (2023)","DOI":"10.1109\/ICRA48891.2023.10161373"},{"key":"23_CR15","doi-asserted-by":"crossref","unstructured":"Saunders, K., Vogiatzis, G., Manso, L.J.: Self-supervised monocular depth estimation: let\u2019s talk about the weather. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (2023)","DOI":"10.1109\/ICCV51070.2023.00818"},{"key":"23_CR16","doi-asserted-by":"crossref","unstructured":"Gasperini, S., et al.: Robust monocular depth estimation under challenging conditions. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (2023)","DOI":"10.1109\/ICCV51070.2023.00751"},{"key":"23_CR17","doi-asserted-by":"crossref","unstructured":"Wang, Z., et al.: Image quality assessment: from error visibility to structural similarity. IEEE Trans. Image Process. 13(4), 600\u2013612 (2004)","DOI":"10.1109\/TIP.2003.819861"},{"key":"23_CR18","doi-asserted-by":"crossref","unstructured":"Godard, C., Aodha, O.M., Brostow, G.J.: Unsupervised monocular depth estimation with left-right consistency. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2017)","DOI":"10.1109\/CVPR.2017.699"},{"key":"23_CR19","doi-asserted-by":"crossref","unstructured":"Geiger, A., et al.: Vision meets robotics: the KITTI dataset. Int. J. Robot. Res. 32(11), 1231\u20141237 (2013)","DOI":"10.1177\/0278364913491297"},{"key":"23_CR20","doi-asserted-by":"crossref","unstructured":"Eigen, D., Fergus, R.: Predicting depth, surface normals and semantic labels with a common multi-scale convolutional architecture. In: Proceedings of the IEEE International Conference on Computer Vision (2015)","DOI":"10.1109\/ICCV.2015.304"},{"issue":"5","key":"23_CR21","doi-asserted-by":"publisher","first-page":"824","DOI":"10.1109\/TPAMI.2008.132","volume":"31","author":"A Saxena","year":"2008","unstructured":"Saxena, A., Sun, M., Ng, A.Y.: Make3d: learning 3d scene structure from a single still image. IEEE Trans. Pattern Anal. Mach. Intell. 31(5), 824\u2013840 (2008)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"23_CR22","doi-asserted-by":"crossref","unstructured":"He, K., et al.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"23_CR23","doi-asserted-by":"crossref","unstructured":"Russakovsky, O., et al.: Imagenet large scale visual recognition challenge. Int. J. Comput. Vis. 115, 211\u2013252 (2015)","DOI":"10.1007\/s11263-015-0816-y"},{"key":"23_CR24","doi-asserted-by":"crossref","unstructured":"Xiong, M., et al.: Self-supervised monocular depth and visual odometry learning with scale-consistent geometric constraints. In: Proceedings of the Twenty-Ninth International Conference on International Joint Conferences on Artificial Intelligence (2021)","DOI":"10.24963\/ijcai.2020\/134"},{"key":"23_CR25","doi-asserted-by":"crossref","unstructured":"Dikov, G., van Vugt, J.: Variational depth networks: uncertainty-aware monocular self-supervised depth estimation. In: European Conference on Computer Vision. Springer Nature Switzerland, Cham (2022)","DOI":"10.1007\/978-3-031-25085-9_3"},{"key":"23_CR26","doi-asserted-by":"crossref","unstructured":"Song, X., et al.: Unsupervised monocular estimation of depth and visual odometry using attention and depth-pose consistency loss. IEEE Trans. Multimedia (2023)","DOI":"10.1109\/TMM.2023.3312950"},{"key":"23_CR27","doi-asserted-by":"crossref","unstructured":"Marsal, R., et al.: MonoProb: self-supervised monocular depth estimation with interpretable uncertainty. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision (2024)","DOI":"10.1109\/WACV57701.2024.00360"},{"key":"23_CR28","doi-asserted-by":"crossref","unstructured":"Xu, Y., et al.: Unsupervised learning of depth estimation and camera pose with multi-scale GANs. IEEE Trans. Intell. Transp. Syst. 23(10), 17039\u201317047 (2022)","DOI":"10.1109\/TITS.2021.3093592"},{"key":"23_CR29","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 (2020)"},{"key":"23_CR30","doi-asserted-by":"crossref","unstructured":"Li, J., et al.: Unsupervised monocular depth estimation with semantic reconstruction using dual-discriminator generative adversarial. In: International Conference on Neural Information Processing. Springer Nature, Singapore (2023)","DOI":"10.1007\/978-981-99-8126-7_31"},{"key":"23_CR31","unstructured":"Jung, A.: Imgaug documentation. Readthedocs.io, June 25 (2019)"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition and Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-97-8508-7_23","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,2]],"date-time":"2024-11-02T06:16:31Z","timestamp":1730528191000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-8508-7_23"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,3]]},"ISBN":["9789819785070","9789819785087"],"references-count":31,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-8508-7_23","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,11,3]]},"assertion":[{"value":"3 November 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chinese Conference on Pattern Recognition and Computer Vision  (PRCV)","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Urumqi","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","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":"18 October 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccprcv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/2024.prcv.cn\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}