{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T14:56:44Z","timestamp":1782313004496,"version":"3.54.5"},"publisher-location":"Cham","reference-count":40,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031915680","type":"print"},{"value":"9783031915697","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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\/978-3-031-91569-7_12","type":"book-chapter","created":{"date-parts":[[2025,5,24]],"date-time":"2025-05-24T12:50:05Z","timestamp":1748091005000},"page":"175-189","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Towards Robust Monocular Depth Estimation in\u00a0Non-lambertian Surfaces"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-8018-0458","authenticated-orcid":false,"given":"Junrui","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-7799-3407","authenticated-orcid":false,"given":"Jiaqi","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-2314-3992","authenticated-orcid":false,"given":"Yachuan","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2785-9638","authenticated-orcid":false,"given":"Yiran","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-7996-8927","authenticated-orcid":false,"given":"Jinghong","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2423-4835","authenticated-orcid":false,"given":"Liao","family":"Shen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9223-1863","authenticated-orcid":false,"given":"Zhiguo","family":"Cao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,5,12]]},"reference":[{"key":"12_CR1","unstructured":"Bhat, S.F., Birkl, R., Wofk, D., Wonka, P., M\u00fcller, M.: Zoedepth: zero-shot transfer by combining relative and metric depth. arXiv (2023)"},{"key":"12_CR2","doi-asserted-by":"crossref","unstructured":"Chang, A.X., et al.: Matterport3d: learning from RGB-D data in indoor environments. In: 3D Vision (2017)","DOI":"10.1109\/3DV.2017.00081"},{"key":"12_CR3","doi-asserted-by":"crossref","unstructured":"Chung, J., Oh, J., Lee, K.M.: Depth-regularized optimization for 3d gaussian splatting in few-shot images. In: CVPRW (2024)","DOI":"10.1109\/CVPRW63382.2024.00086"},{"key":"12_CR4","doi-asserted-by":"crossref","unstructured":"Costanzino, A., Ramirez, P.Z., Poggi, M., Tosi, F., Mattoccia, S., Stefano, L.D.: Learning depth estimation for transparent and mirror surfaces. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00848"},{"key":"12_CR5","doi-asserted-by":"crossref","unstructured":"Cui, Z., Sheng, H., Yang, D., Wang, S., Chen, R., Ke, W.: Light field depth estimation for non-lambertian objects via adaptive cross operator. IEEE Trans. Circ. Syst. Video Technol. (2023)","DOI":"10.1109\/TCSVT.2023.3292884"},{"key":"12_CR6","doi-asserted-by":"crossref","unstructured":"Dai, A., Chang, A.X., Savva, M., Halber, M., Funkhouser, T.A., Nie\u00dfner, M.: Scannet: richly-annotated 3D reconstructions of indoor scenes. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.261"},{"key":"12_CR7","unstructured":"Gui, M., et al.: Depthfm: fast monocular depth estimation with flow matching. arXiv (2024)"},{"key":"12_CR8","doi-asserted-by":"crossref","unstructured":"Guizilini, V., Vasiljevic, I., Chen, D., Ambrus, R., Gaidon, A.: Towards zero-shot scale-aware monocular depth estimation. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00847"},{"key":"12_CR9","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. In: NIPS (2020)"},{"key":"12_CR10","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. CoRR (2024)","DOI":"10.1109\/TPAMI.2024.3444912"},{"key":"12_CR11","doi-asserted-by":"crossref","unstructured":"Huang, T., Dong, B., Lin, J., Liu, X., Lau, R.W.H., Zuo, W.: Symmetry-aware transformer-based mirror detection. In: AAAI (2023)","DOI":"10.1609\/aaai.v37i1.25173"},{"key":"12_CR12","doi-asserted-by":"crossref","unstructured":"Ignatov, A., et\u00a0al.: Efficient single-image depth estimation on mobile devices, mobile AI & AIM 2022 challenge: report. In: ECCV (2022)","DOI":"10.1007\/978-3-031-25066-8_4"},{"key":"12_CR13","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: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.00907"},{"key":"12_CR14","unstructured":"Krasin, I., et al.: Openimages: a public dataset for large-scale multi-label and multi-class image classification (2017). https:\/\/storage.googleapis.com\/openimages\/web\/index.html"},{"key":"12_CR15","doi-asserted-by":"crossref","unstructured":"Li, J., et al.: Dngaussian: optimizing sparse-view 3D gaussian radiance fields with global-local depth normalization. In: CVPRW (2024)","DOI":"10.1109\/CVPR52733.2024.01963"},{"key":"12_CR16","doi-asserted-by":"crossref","unstructured":"Li, J., et al.: Diffusion-augmented depth prediction with sparse annotations. In: ACMMM (2023)","DOI":"10.1145\/3581783.3611807"},{"key":"12_CR17","doi-asserted-by":"crossref","unstructured":"Li, X., Cao, Z., Sun, H., Zhang, J., Xian, K., Lin, G.: 3D cinemagraphy from a single image. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00446"},{"key":"12_CR18","doi-asserted-by":"crossref","unstructured":"Li, Z., Snavely, N.: Megadepth: learning single-view depth prediction from internet photos. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00218"},{"key":"12_CR19","doi-asserted-by":"crossref","unstructured":"Mei, H., et al.: Depth-aware mirror segmentation. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00306"},{"key":"12_CR20","unstructured":"Oquab, M., et al.: Dinov2: learning robust visual features without supervision. arXiv (2023)"},{"key":"12_CR21","doi-asserted-by":"crossref","unstructured":"Ramirez, P.Z., et al.: Booster: a benchmark for depth from images of specular and transparent surfaces. TPAMI (2024)","DOI":"10.1109\/TPAMI.2023.3323858"},{"key":"12_CR22","doi-asserted-by":"crossref","unstructured":"Ramirez, P.Z., Tosi, F., Poggi, M., Salti, S., Mattoccia, S., Stefano, L.D.: Open challenges in deep stereo: the booster dataset. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.02049"},{"key":"12_CR23","doi-asserted-by":"crossref","unstructured":"Ramirez, P.Z., et al.: NTIRE 2023 challenge on HR depth from images of specular and transparent surfaces. In: CVPRW (2023)","DOI":"10.1109\/CVPRW59228.2023.00143"},{"key":"12_CR24","doi-asserted-by":"crossref","unstructured":"Ranftl, R., Bochkovskiy, A., Koltun, V.: Vision transformers for dense prediction. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.01196"},{"key":"12_CR25","unstructured":"Ranftl, R., Lasinger, K., Hafner, D., Schindler, K., Koltun, V.: Towards robust monocular depth estimation: mixing datasets for zero-shot cross-dataset transfer. TPAMI (2020)"},{"key":"12_CR26","doi-asserted-by":"crossref","unstructured":"Roberts, M., et al.: Hypersim: a photorealistic synthetic dataset for holistic indoor scene understanding. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.01073"},{"key":"12_CR27","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"12_CR28","doi-asserted-by":"crossref","unstructured":"Shen, L., et al.: Make-it-4D: synthesizing a consistent long-term dynamic scene video from a single image. In: ACMMM (2023)","DOI":"10.1145\/3581783.3612033"},{"key":"12_CR29","doi-asserted-by":"crossref","unstructured":"Silberman, N., Hoiem, D., Kohli, P., Fergus, R.: Indoor segmentation and support inference from RGBD images. In: ECCV (2012)","DOI":"10.1007\/978-3-642-33715-4_54"},{"key":"12_CR30","doi-asserted-by":"crossref","unstructured":"Tan, J., Lin, W., Chang, A.X., Savva, M.: Mirror3d: depth refinement for mirror surfaces. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.01573"},{"key":"12_CR31","unstructured":"Vaswani, A., et al.: Attention is all you need. In: NIPS (2017)"},{"key":"12_CR32","doi-asserted-by":"crossref","unstructured":"Wang, Y., Chao, W., Garg, D., Hariharan, B., Campbell, M.E., Weinberger, K.Q.: Pseudo-lidar from visual depth estimation: bridging the gap in 3D object detection for autonomous driving. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00864"},{"key":"12_CR33","doi-asserted-by":"crossref","unstructured":"Wang, Y., et al.: Neural video depth stabilizer. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00868"},{"key":"12_CR34","doi-asserted-by":"crossref","unstructured":"Xian, K., et al.: Monocular relative depth perception with web stereo data supervision. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00040"},{"key":"12_CR35","doi-asserted-by":"crossref","unstructured":"Yang, B., Rosa, S., Markham, A., Trigoni, N., Wen, H.: Dense 3D object reconstruction from a single depth view. TPAMI (2019)","DOI":"10.1109\/TPAMI.2018.2868195"},{"key":"12_CR36","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: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.00987"},{"key":"12_CR37","unstructured":"Yang, L., et al.: Depth anything V2. CoRR (2024)"},{"key":"12_CR38","doi-asserted-by":"crossref","unstructured":"Yin, W., et al.: Metric3d: towards zero-shot metric 3D prediction from a single image. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00830"},{"key":"12_CR39","unstructured":"Zama\u00a0Ramirez, P., et al.: Tricky 2024 challenge on monocular depth from images of specular and transparent surfaces. In: ECCVW (2024)"},{"key":"12_CR40","unstructured":"Zama\u00a0Ramirez, P., et al.: NTIRE 2024 challenge on HR depth from images of specular and transparent surfaces. In: CVPRW (2024)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024 Workshops"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-91569-7_12","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,24]],"date-time":"2025-05-24T12:50:19Z","timestamp":1748091019000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-91569-7_12"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9783031915680","9783031915697"],"references-count":40,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-91569-7_12","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"12 May 2025","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"}}]}}