{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T19:08:29Z","timestamp":1788894509418,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":48,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032370341","type":"print"},{"value":"9783032370358","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\/978-3-032-37035-8_11","type":"book-chapter","created":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T18:53:51Z","timestamp":1788893631000},"page":"194-211","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["FoundDP: Revisiting Weak Disparity Observability in\u00a0Dual-Pixel Depth Estimation"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-8152-5703","authenticated-orcid":false,"given":"Fengchen","family":"He","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-6803-5463","authenticated-orcid":false,"given":"Hao","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dayang","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tingwei","family":"Quan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shaoqun","family":"Zeng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,9]]},"reference":[{"key":"11_CR1","doi-asserted-by":"crossref","unstructured":"Abuolaim, A., Afifi, M., Brown, M.S.: Improving single-image defocus deblurring: how dual-pixel images help through multi-task learning. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 1231\u20131239 (2022)","DOI":"10.1109\/WACV51458.2022.00016"},{"key":"11_CR2","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"111","DOI":"10.1007\/978-3-030-58607-2_7","volume-title":"Computer Vision \u2013 ECCV 2020","author":"A Abuolaim","year":"2020","unstructured":"Abuolaim, A., Brown, M.S.: Defocus deblurring using dual-pixel data. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12355, pp. 111\u2013126. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58607-2_7"},{"key":"11_CR3","doi-asserted-by":"crossref","unstructured":"Bastidas, A.A., Tang, H.: Channel attention networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (2019)","DOI":"10.1109\/CVPRW.2019.00117"},{"key":"11_CR4","doi-asserted-by":"crossref","unstructured":"Choi, M., Lee, H., Lee, H.: Exploring positional characteristics of dual-pixel data for camera autofocus. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 13158\u201313168 (2023)","DOI":"10.1109\/ICCV51070.2023.01210"},{"key":"11_CR5","first-page":"O1","volume":"93","author":"L Doehyung","year":"2025","unstructured":"Doehyung, L., Zhuofeng, W., Yusuke, M., Masatoshi, O.: FMDP: leveraging a foundation model for dual-pixel disparity estimation. IEICE Proc. Ser. 93, O1-1 (2025)","journal-title":"IEICE Proc. Ser."},{"key":"11_CR6","unstructured":"Dosovitskiy, A.: An image is worth 16 $$\\times $$ 16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"11_CR7","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, vol. 27 (2014)"},{"key":"11_CR8","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":"11_CR9","doi-asserted-by":"crossref","unstructured":"Garg, R., Wadhwa, N., Ansari, S., Barron, J.T.: Learning single camera depth estimation using dual-pixels. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 7628\u20137637 (2019)","DOI":"10.1109\/ICCV.2019.00772"},{"key":"11_CR10","doi-asserted-by":"crossref","unstructured":"Ghanekar, B., et al.: Passive snapshot coded aperture dual-pixel RGB-D imaging. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 25348\u201325357 (2024)","DOI":"10.1109\/CVPR52733.2024.02395"},{"key":"11_CR11","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":"11_CR12","doi-asserted-by":"crossref","unstructured":"He, F., Zhao, D., Xu, H., Quan, T., Zeng, S.: Simulating dual-pixel images from ray tracing for depth estimation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 26106\u201326115 (2025)","DOI":"10.1109\/ICCV51701.2025.02422"},{"key":"11_CR13","doi-asserted-by":"crossref","unstructured":"Jiang, H., et al.: Defom-stereo: depth foundation model based stereo matching. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 21857\u201321867 (2025)","DOI":"10.1109\/CVPR52734.2025.02036"},{"key":"11_CR14","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":"11_CR15","doi-asserted-by":"crossref","unstructured":"Kim, D., Jang, H., Kim, I., Kim, M.H.: Spatio-focal bidirectional disparity estimation from a dual-pixel image. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5023\u20135032 (2023)","DOI":"10.1109\/CVPR52729.2023.00486"},{"issue":"2","key":"11_CR16","first-page":"123","volume":"4","author":"M Kobayashi","year":"2016","unstructured":"Kobayashi, M., et al.: A low noise and high sensitivity image sensor with imaging and phase-difference detection AF in all pixels. ITE Trans. Media Technol. Appl. 4(2), 123\u2013128 (2016)","journal-title":"ITE Trans. Media Technol. Appl."},{"key":"11_CR17","doi-asserted-by":"crossref","unstructured":"Li, F., Guo, H., Santo, H., Okura, F., Matsushita, Y.: Learning to synthesize photorealistic dual-pixel images from RGBD frames. In: 2023 IEEE International Conference on Computational Photography (ICCP), pp. 1\u201311. IEEE (2023)","DOI":"10.1109\/ICCP56744.2023.10233839"},{"key":"11_CR18","doi-asserted-by":"crossref","unstructured":"Li, Y., Monno, Y., Okutomi, M.: Dual-pixel raindrop removal. IEEE Trans. Pattern Anal. Mach. Intell. (2024)","DOI":"10.1109\/TPAMI.2024.3442955"},{"key":"11_CR19","doi-asserted-by":"publisher","first-page":"128880","DOI":"10.1016\/j.neucom.2024.128880","volume":"616","author":"Y Li","year":"2025","unstructured":"Li, Y., Yi, Y., Shu, X., Ren, D., Li, Q., Zuo, W.: Learning dual-pixel alignment for defocus deblurring. Neurocomputing 616, 128880 (2025)","journal-title":"Neurocomputing"},{"key":"11_CR20","doi-asserted-by":"crossref","unstructured":"Lin, H., et al.: Prompting depth anything for 4k resolution accurate metric depth estimation. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 17070\u201317080 (2025)","DOI":"10.1109\/CVPR52734.2025.01591"},{"key":"11_CR21","doi-asserted-by":"crossref","unstructured":"Monin, S., Katz, S., Evangelidis, G.: Continuous cost aggregation for dual-pixel disparity extraction. In: 2024 International Conference on 3D Vision (3DV), pp. 675\u2013684. IEEE (2024)","DOI":"10.1109\/3DV62453.2024.00029"},{"key":"11_CR22","doi-asserted-by":"crossref","unstructured":"Pan, L., Chowdhury, S., Hartley, R., Liu, M., Zhang, H., Li, H.: Dual pixel exploration: simultaneous depth estimation and image restoration. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4340\u20134349 (2021)","DOI":"10.1109\/CVPR46437.2021.00432"},{"key":"11_CR23","doi-asserted-by":"crossref","unstructured":"Pan, L., et al.: Weakly-supervised depth estimation and image deblurring via dual-pixel sensors. IEEE Trans. Pattern Anal. Mach. Intell. (2024)","DOI":"10.1109\/TPAMI.2024.3458974"},{"key":"11_CR24","doi-asserted-by":"crossref","unstructured":"Piccinelli, L., et al.: Unidepth: universal monocular metric depth estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10106\u201310116 (2024)","DOI":"10.1109\/CVPR52733.2024.00963"},{"key":"11_CR25","doi-asserted-by":"crossref","unstructured":"Punnappurath, A., Abuolaim, A., Afifi, M., Brown, M.S.: Modeling defocus-disparity in dual-pixel sensors. In: 2020 IEEE International Conference on Computational Photography (ICCP), pp. 1\u201312. IEEE (2020)","DOI":"10.1109\/ICCP48838.2020.9105278"},{"key":"11_CR26","doi-asserted-by":"crossref","unstructured":"Punnappurath, A., Brown, M.S.: Reflection removal using a dual-pixel sensor. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1556\u20131565 (2019)","DOI":"10.1109\/CVPR.2019.00165"},{"key":"11_CR27","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":"11_CR28","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."},{"issue":"4","key":"11_CR29","first-page":"1","volume":"43","author":"Z Shi","year":"2024","unstructured":"Shi, Z., et al.: Split-aperture 2-in-1 computational cameras. ACM Trans. Graph. (TOG) 43(4), 1\u201319 (2024)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"11_CR30","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"},{"issue":"06","key":"11_CR31","doi-asserted-by":"publisher","first-page":"11","DOI":"10.4236\/jcc.2013.16003","volume":"1","author":"P \u015aliwi\u0144ski","year":"2013","unstructured":"\u015aliwi\u0144ski, P., Wachel, P.: A simple model for on-sensor phase-detection autofocusing algorithm. J. Comput. Commun. 1(06), 11 (2013)","journal-title":"J. Comput. Commun."},{"issue":"4","key":"11_CR32","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3197517.3201329","volume":"37","author":"N Wadhwa","year":"2018","unstructured":"Wadhwa, N., et al.: Synthetic depth-of-field with a single-camera mobile phone. ACM Trans. Graph. (ToG) 37(4), 1\u201313 (2018)","journal-title":"ACM Trans. Graph. (ToG)"},{"key":"11_CR33","doi-asserted-by":"crossref","unstructured":"Wang, Q., Wu, B., Zhu, P., Li, P., Zuo, W., Hu, Q.: ECA-Net: efficient channel attention for deep convolutional neural networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11534\u201311542 (2020)","DOI":"10.1109\/CVPR42600.2020.01155"},{"key":"11_CR34","doi-asserted-by":"crossref","unstructured":"Wang, R., et al.: Moge: unlocking accurate monocular geometry estimation for open-domain images with optimal training supervision. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 5261\u20135271 (2025)","DOI":"10.1109\/CVPR52734.2025.00496"},{"key":"11_CR35","unstructured":"Wang, Z., Cet al.: Depth anything with any prior. arXiv preprint arXiv:2505.10565 (2025)"},{"key":"11_CR36","doi-asserted-by":"crossref","unstructured":"Wen, B., Trepte, M., Aribido, J., Kautz, J., Gallo, O., Birchfield, S.: Foundationstereo: zero-shot stereo matching. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5249\u20135260 (2025)","DOI":"10.1109\/CVPR52734.2025.00495"},{"key":"11_CR37","doi-asserted-by":"crossref","unstructured":"Wu, K., Peng, H., Chen, M., Fu, J., Chao, H.: Rethinking and improving relative position encoding for vision transformer. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10033\u201310041 (2021)","DOI":"10.1109\/ICCV48922.2021.00988"},{"key":"11_CR38","doi-asserted-by":"crossref","unstructured":"Xin, S., et al.: Defocus map estimation and deblurring from a single dual-pixel image. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 2228\u20132238 (2021)","DOI":"10.1109\/ICCV48922.2021.00223"},{"key":"11_CR39","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":"11_CR40","doi-asserted-by":"crossref","unstructured":"Yang, H., Pan, L., Yang, Y., Hartley, R., Liu, M.: LDP: language-driven dual-pixel image defocus deblurring network. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 24078\u201324087 (2024)","DOI":"10.1109\/CVPR52733.2024.02273"},{"key":"11_CR41","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":"11_CR42","doi-asserted-by":"crossref","unstructured":"Yang, L., et al.: Depth anything v2. In: Advances in Neural Information Processing Systems, vol. 37, pp. 21875\u201321911 (2024)","DOI":"10.52202\/079017-0688"},{"key":"11_CR43","doi-asserted-by":"crossref","unstructured":"Yang, Y., Pan, L., Liu, L., Liu, M.: K3DN: disparity-aware kernel estimation for dual-pixel defocus deblurring. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13263\u201313272 (2023)","DOI":"10.1109\/CVPR52729.2023.01274"},{"key":"11_CR44","doi-asserted-by":"crossref","unstructured":"Ye, T., et al.: Prompthaze: prompting real-world dehazing via depth anything model. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a039, pp. 9454\u20139462 (2025)","DOI":"10.1609\/aaai.v39i9.33024"},{"key":"11_CR45","doi-asserted-by":"crossref","unstructured":"Yin, W., et al.: Learning to recover 3D scene shape from a single image. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 204\u2013213 (2021)","DOI":"10.1109\/CVPR46437.2021.00027"},{"key":"11_CR46","doi-asserted-by":"crossref","unstructured":"Yu, H., Song, S., Sun, L., Su, W., Yang, X., Liu, C.: All-directional disparity estimation for real-world QPD images. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 21836\u201321846 (2025)","DOI":"10.1109\/CVPR52734.2025.02034"},{"key":"11_CR47","doi-asserted-by":"crossref","unstructured":"Yu, K., Pan, L., Liu, L., Liang, W.: Enhanced dual-pixel image reflection removal via gaussian splatting. In: Proceedings of the 33rd ACM International Conference on Multimedia, pp. 7766\u20137775 (2025)","DOI":"10.1145\/3746027.3755094"},{"key":"11_CR48","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"582","DOI":"10.1007\/978-3-030-58452-8_34","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Y Zhang","year":"2020","unstructured":"Zhang, Y., Wadhwa, N., Orts-Escolano, S., H\u00e4ne, C., Fanello, S., Garg, R.: Du2Net: learning depth estimation from dual-cameras and dual-pixels. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 582\u2013598. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_34"}],"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\/978-3-032-37035-8_11","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T18:53:56Z","timestamp":1788893636000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37035-8_11"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032370341","9783032370358"],"references-count":48,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37035-8_11","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":"9 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"}}]}}