{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T05:45:20Z","timestamp":1777873520564,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":95,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,8,3]]},"DOI":"10.1145\/3711896.3737394","type":"proceedings-article","created":{"date-parts":[[2025,8,3]],"date-time":"2025-08-03T21:03:27Z","timestamp":1754255007000},"page":"5355-5366","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["MonoDeMB: Comprehensive Monocular DepthMap Benchmark"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-8205-6591","authenticated-orcid":false,"given":"Vaagn","family":"Chopuryan","sequence":"first","affiliation":[{"name":"Sber AI, Moscow, Russian Federation"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-1315-7711","authenticated-orcid":false,"given":"Mikhail","family":"Kuznetsov","sequence":"additional","affiliation":[{"name":"Sber AI, Moscow, Russian Federation and Skolkovo Institute of Science and Technology, Moscow, Russian Federation"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7810-8033","authenticated-orcid":false,"given":"Vasilii","family":"Latonov","sequence":"additional","affiliation":[{"name":"Sber AI, Moscow, Russian Federation"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-1148-8425","authenticated-orcid":false,"given":"Vladimir","family":"Mashurov","sequence":"additional","affiliation":[{"name":"Sber AI, Moscow, Russian Federation and ITMO National Research University, Saint-Petersburg, Russian Federation"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4189-5739","authenticated-orcid":false,"given":"Natalia","family":"Semenova","sequence":"additional","affiliation":[{"name":"Sber AI, Moscow, Russian Federation and Artificial Intelligence Research Institute, Moscow, Russian Federation"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,8,3]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161161"},{"key":"e_1_3_2_2_2_1","volume-title":"Yubin Kuang, and Peter Kontschieder.","author":"Antequera Manuel L\u00f3pez","year":"2020","unstructured":"Manuel L\u00f3pez Antequera, Pau Gargallo, Markus Hofinger, Samuel Rota Bul\u00f2, Yubin Kuang, and Peter Kontschieder. 2020. Mapillary Planet-Scale Depth Dataset. In Computer Vision - ECCV 2020, Andrea Vedaldi, Horst Bischof, Thomas Brox, and Jan-Michael Frahm (Eds.). Springer International Publishing, Cham, 589-604."},{"key":"e_1_3_2_2_3_1","volume-title":"a large-scale high-resolution outdoor stereo dataset. Scientific data 6, 1","author":"Bauer Zuria","year":"2019","unstructured":"Zuria Bauer, Francisco Gomez-Donoso, Edmanuel Cruz, Sergio Orts-Escolano, and Miguel Cazorla. 2019. UASOL, a large-scale high-resolution outdoor stereo dataset. Scientific data 6, 1 (2019), 162."},{"key":"e_1_3_2_2_4_1","volume-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. 4009-4018","author":"Bhat Shariq Farooq","year":"2021","unstructured":"Shariq Farooq Bhat, Ibraheem Alhashim, and Peter Wonka. 2021. Adabins: Depth estimation using adaptive bins. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. 4009-4018."},{"key":"e_1_3_2_2_5_1","volume-title":"Zoedepth: Zero-shot transfer by combining relative and metric depth. arXiv preprint arXiv:2302.12288","author":"Bhat Shariq Farooq","year":"2023","unstructured":"Shariq Farooq Bhat, Reiner Birkl, Diana Wofk, Peter Wonka, and Matthias M\u00fcller. 2023. Zoedepth: Zero-shot transfer by combining relative and metric depth. arXiv preprint arXiv:2302.12288 (2023)."},{"key":"e_1_3_2_2_6_1","volume-title":"arXiv e-prints","author":"Cabon Yohann","year":"2020","unstructured":"Yohann Cabon, Naila Murray, and Martin Humenberger. 2020. Virtual KITTI 2. arXiv e-prints (2020), arXiv-2001."},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2017.00081"},{"key":"e_1_3_2_2_9_1","volume-title":"Single-image depth perception in the wild. Advances in neural information processing systems 29","author":"Chen Weifeng","year":"2016","unstructured":"Weifeng Chen, Zhao Fu, Dawei Yang, and Jia Deng. 2016. Single-image depth perception in the wild. Advances in neural information processing systems 29 (2016)."},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2021.114877"},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.261"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2020.103701"},{"key":"e_1_3_2_2_14_1","volume-title":"Samir Yitzhak Gadre, et al","author":"Deitke Matt","year":"2023","unstructured":"Matt Deitke, Ruoshi Liu, Matthew Wallingford, Huong Ngo, Oscar Michel, Aditya Kusupati, Alan Fan, Christian Laforte, Vikram Voleti, Samir Yitzhak Gadre, et al. 2023. Objaverse-xl: A universe of 10m 3d objects. arXiv preprint arXiv:2307.05663 (2023)."},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01263"},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3160741"},{"key":"e_1_3_2_2_17_1","volume-title":"An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929","author":"Dosovitskiy Alexey","year":"2020","unstructured":"Alexey Dosovitskiy. 2020. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)."},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01061"},{"key":"e_1_3_2_2_19_1","volume-title":"Depth map prediction from a single image using a multi-scale deep network. Advances in neural information processing systems 27","author":"Eigen David","year":"2014","unstructured":"David Eigen, Christian Puhrsch, and Rob Fergus. 2014. Depth map prediction from a single image using a multi-scale deep network. Advances in neural information processing systems 27 (2014)."},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00214"},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72670-5_14"},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"crossref","unstructured":"Yasutaka Furukawa Carlos Hern\u00e1ndez et al. 2015. Multi-view stereo: A tutorial. Foundations and Trends\u00ae in Computer Graphics and Vision 9 1-2 (2015) 1-148.","DOI":"10.1561\/0600000052"},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2022.3151629"},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3068942"},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913491297"},{"key":"e_1_3_2_2_26_1","volume-title":"Maximilian M\u00fchlegg, Sebastian Dorn, et al.","author":"Geyer Jakob","year":"2020","unstructured":"Jakob Geyer, Yohannes Kassahun, Mentar Mahmudi, Xavier Ricou, Rupesh Durgesh, Andrew S Chung, Lorenz Hauswald, Viet Hoang Pham, Maximilian M\u00fchlegg, Sebastian Dorn, et al. 2020. A2d2: Audi autonomous driving dataset. arXiv preprint arXiv:2004.06320 (2020)."},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00393"},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00256"},{"key":"e_1_3_2_2_29_1","volume-title":"Conference on Robot Learning. PMLR, 409-418","author":"Houston John","year":"2021","unstructured":"John Houston, Guido Zuidhof, Luca Bergamini, Yawei Ye, Long Chen, Ashesh Jain, Sammy Omari, Vladimir Iglovikov, and Peter Ondruska. 2021. One thousand and one hours: Self-driving motion prediction dataset. In Conference on Robot Learning. PMLR, 409-418."},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10341917"},{"key":"e_1_3_2_2_31_1","volume-title":"Metric3D v2: A Versatile Monocular Geometric Foundation Model for Zero-shot Metric Depth and Surface Normal Estimation. arXiv preprint arXiv:2404.15506","author":"Hu Mu","year":"2024","unstructured":"Mu Hu, Wei Yin, Chi Zhang, Zhipeng Cai, Xiaoxiao Long, Hao Chen, Kaixuan Wang, Gang Yu, Chunhua Shen, and Shaojie Shen. 2024. Metric3D v2: A Versatile Monocular Geometric Foundation Model for Zero-shot Metric Depth and Surface Normal Estimation. arXiv preprint arXiv:2404.15506 (2024)."},{"key":"e_1_3_2_2_32_1","volume-title":"Holopix50k: A Large-Scale In-the-wild Stereo Image Dataset. arXiv e-prints","author":"Hua Yiwen","year":"2020","unstructured":"Yiwen Hua, Puneet Kohli, Pritish Uplavikar, Anand Ravi, Saravana Gunaseelan, Jason Orozco, and Edward Li. 2020. Holopix50k: A Large-Scale In-the-wild Stereo Image Dataset. arXiv e-prints (2020), arXiv-2003."},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01255"},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00907"},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.3390\/s20082272"},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2836318"},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"crossref","unstructured":"Alina Kuznetsova Hassan Rom Neil Alldrin Jasper Uijlings Ivan Krasin Jordi Pont-Tuset Shahab Kamali Stefan Popov Matteo Malloci Alexander Kolesnikov et al. 2020. The open images dataset v4: Unified image classification object detection and visual relationship detection at scale. International journal of computer vision 128 7 (2020) 1956-1981.","DOI":"10.1007\/s11263-020-01316-z"},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.3390\/vehicles6010013"},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2016.32"},{"key":"e_1_3_2_2_41_1","volume-title":"Dong Wook Ko, and Il Hong Suh","author":"Lee Jin Han","year":"2019","unstructured":"Jin Han Lee, Myung-Kyu Han, Dong Wook Ko, and Il Hong Suh. 2019. From big to small: Multi-scale local planar guidance for monocular depth estimation. arXiv preprint arXiv:1907.10326 (2019)."},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.365"},{"key":"e_1_3_2_2_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00465"},{"key":"e_1_3_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00218"},{"key":"e_1_3_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"e_1_3_2_2_46_1","doi-asserted-by":"publisher","DOI":"10.3390\/s22145353"},{"key":"e_1_3_2_2_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3060513"},{"key":"e_1_3_2_2_48_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.12.089"},{"key":"e_1_3_2_2_49_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.mlwa.2022.100416"},{"key":"e_1_3_2_2_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/3355089.3356528"},{"key":"e_1_3_2_2_51_1","doi-asserted-by":"publisher","DOI":"10.3390\/drones8020066"},{"key":"e_1_3_2_2_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02057"},{"key":"e_1_3_2_2_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00963"},{"key":"e_1_3_2_2_54_1","volume-title":"Deep learning-based depth estimation methods from monocular image and videos: A comprehensive survey. ACM computing surveys 56, 12","author":"Rajapaksha Uchitha","year":"2024","unstructured":"Uchitha Rajapaksha, Ferdous Sohel, Hamid Laga, Dean Diepeveen, and Mohammed Bennamoun. 2024. Deep learning-based depth estimation methods from monocular image and videos: A comprehensive survey. ACM computing surveys 56, 12 (2024), 1-51."},{"key":"e_1_3_2_2_55_1","volume-title":"et al","author":"Ramakrishnan Santhosh K","year":"2021","unstructured":"Santhosh K Ramakrishnan, Aaron Gokaslan, Erik Wijmans, Oleksandr Maksymets, Alex Clegg, John Turner, Eric Undersander, Wojciech Galuba, Andrew Westbury, Angel X Chang, et al . 2021. Habitat-matterport 3d dataset (hm3d): 1000 large-scale 3d environments for embodied ai. arXiv preprint arXiv:2109.08238 (2021)."},{"key":"e_1_3_2_2_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01196"},{"key":"e_1_3_2_2_57_1","volume-title":"Towards robust monocular depth estimation: Mixing datasets for zero-shot cross-dataset transfer","author":"Ranftl Ren\u00e9","year":"2020","unstructured":"Ren\u00e9 Ranftl, Katrin Lasinger, David Hafner, Konrad Schindler, and Vladlen Koltun. 2020. Towards robust monocular depth estimation: Mixing datasets for zero-shot cross-dataset transfer. IEEE transactions on pattern analysis and machine intelligence 44, 3 (2020), 1623-1637."},{"key":"e_1_3_2_2_58_1","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV). 10912-10922","author":"Roberts Mike","unstructured":"Mike Roberts, Jason Ramapuram, Anurag Ranjan, Atulit Kumar, Miguel Angel Bautista, Nathan Paczan, Russ Webb, and Joshua M. Susskind. 2021. Hypersim: A Photorealistic Synthetic Dataset for Holistic Indoor Scene Understanding. In Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV). 10912-10922."},{"key":"e_1_3_2_2_59_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_2_2_60_1","first-page":"234","volume-title":"Munich","author":"Ronneberger Olaf","year":"2015","unstructured":"Olaf Ronneberger, Philipp Fischer, and Thomas Brox. 2015. U-net: Convolutional networks for biomedical image segmentation. In Medical image computing and computer-assisted intervention-MICCAI 2015: 18th international conference, Munich, Germany, October 5-9, 2015, proceedings, part III 18. Springer, 234-241."},{"key":"e_1_3_2_2_61_1","doi-asserted-by":"crossref","unstructured":"Olga Russakovsky Jia Deng Hao Su Jonathan Krause Sanjeev Satheesh Sean Ma Zhiheng Huang Andrej Karpathy Aditya Khosla Michael Bernstein et al. 2015. Imagenet large scale visual recognition challenge. International journal of computer vision 115 (2015) 211-252.","DOI":"10.1007\/s11263-015-0816-y"},{"key":"e_1_3_2_2_62_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.272"},{"key":"e_1_3_2_2_63_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00852"},{"key":"e_1_3_2_2_64_1","first-page":"746","volume-title":"Florence","author":"Silberman Nathan","year":"2012","unstructured":"Nathan Silberman, Derek Hoiem, Pushmeet Kohli, and Rob Fergus. 2012. Indoor segmentation and support inference from rgbd images. In Computer Vision-ECCV 2012: 12th European Conference on Computer Vision, Florence, Italy, October 7-13, 2012, Proceedings, Part V 12. Springer, 746-760."},{"key":"e_1_3_2_2_65_1","unstructured":"Julian Straub Thomas Whelan Lingni Ma Yufan Chen Erik Wijmans Simon Green Jakob J Engel Raul Mur-Artal Carl Ren Shobhit Verma et al. 2019. The Replica dataset: A digital replica of indoor spaces. arXiv preprint arXiv:1906.05797 (2019)."},{"key":"e_1_3_2_2_66_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00252"},{"key":"e_1_3_2_2_67_1","volume-title":"Diode: A dense indoor and outdoor depth dataset. arXiv preprint arXiv:1908.00463","author":"Vasiljevic Igor","year":"2019","unstructured":"Igor Vasiljevic, Nick Kolkin, Shanyi Zhang, Ruotian Luo, Haochen Wang, Falcon Z Dai, Andrea F Daniele, Mohammadreza Mostajabi, Steven Basart, Matthew R Walter, et al. 2019. Diode: A dense indoor and outdoor depth dataset. arXiv preprint arXiv:1908.00463 (2019)."},{"key":"e_1_3_2_2_68_1","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2019.00046"},{"key":"e_1_3_2_2_69_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2023.105846"},{"key":"e_1_3_2_2_70_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICME51207.2021.9428423"},{"key":"e_1_3_2_2_71_1","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341801"},{"key":"e_1_3_2_2_72_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00265"},{"key":"e_1_3_2_2_73_1","volume-title":"Jhony Kaesemodel Pontes, et al","author":"Wilson Benjamin","year":"2023","unstructured":"Benjamin Wilson, William Qi, Tanmay Agarwal, John Lambert, Jagjeet Singh, Siddhesh Khandelwal, Bowen Pan, Ratnesh Kumar, Andrew Hartnett, Jhony Kaesemodel Pontes, et al. 2023. Argoverse 2: Next generation datasets for self-driving perception and forecasting. arXiv preprint arXiv:2301.00493 (2023)."},{"key":"e_1_3_2_2_74_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00379"},{"key":"e_1_3_2_2_75_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00040"},{"key":"e_1_3_2_2_76_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00069"},{"key":"e_1_3_2_2_77_1","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC48978.2021.9565009"},{"key":"e_1_3_2_2_78_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"e_1_3_2_2_79_1","volume-title":"What Matters When Repurposing Diffusion Models for General Dense Perception Tasks? arXiv preprint arXiv:2403.06090","author":"Xu Guangkai","year":"2024","unstructured":"Guangkai Xu, Yongtao Ge, Mingyu Liu, Chengxiang Fan, Kangyang Xie, Zhiyue Zhao, Hao Chen, and Chunhua Shen. 2024. What Matters When Repurposing Diffusion Models for General Dense Perception Tasks? arXiv preprint arXiv:2403.06090 (2024)."},{"key":"e_1_3_2_2_80_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00099"},{"key":"e_1_3_2_2_81_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01596"},{"key":"e_1_3_2_2_82_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00987"},{"key":"e_1_3_2_2_83_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00186"},{"key":"e_1_3_2_2_84_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00578"},{"key":"e_1_3_2_2_85_1","volume-title":"Diversedepth: Affine-invariant depth prediction using diverse data. arXiv preprint arXiv:2002.00569","author":"Yin Wei","year":"2020","unstructured":"Wei Yin, Xinlong Wang, Chunhua Shen, Yifan Liu, Zhi Tian, Songcen Xu, Chang-ming Sun, and Dou Renyin. 2020. Diversedepth: Affine-invariant depth prediction using diverse data. arXiv preprint arXiv:2002.00569 (2020)."},{"key":"e_1_3_2_2_86_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00830"},{"key":"e_1_3_2_2_87_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00027"},{"key":"e_1_3_2_2_88_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161471"},{"key":"e_1_3_2_2_89_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00271"},{"key":"e_1_3_2_2_90_1","volume-title":"Lsun: Construction of a large-scale image dataset using deep learning with humans in the loop. arXiv preprint arXiv:1506.03365","author":"Yu Fisher","year":"2015","unstructured":"Fisher Yu, Ari Seff, Yinda Zhang, Shuran Song, Thomas Funkhouser, and Jianxiong Xiao. 2015. Lsun: Construction of a large-scale image dataset using deep learning with humans in the loop. arXiv preprint arXiv:1506.03365 (2015)."},{"key":"e_1_3_2_2_91_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00389"},{"key":"e_1_3_2_2_92_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00391"},{"key":"e_1_3_2_2_93_1","first-page":"14128","article-title":"Hierarchical normalization for robust monocular depth estimation","volume":"35","author":"Zhang Chi","year":"2022","unstructured":"Chi Zhang, Wei Yin, Billzb Wang, Gang Yu, Bin Fu, and Chunhua Shen. 2022. Hierarchical normalization for robust monocular depth estimation. Advances in Neural Information Processing Systems 35 (2022), 14128-14139.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_94_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01485"},{"key":"e_1_3_2_2_95_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2723009"}],"event":{"name":"KDD '25: The 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining","location":"Toronto ON Canada","acronym":"KDD '25","sponsor":["SIGKDD ACM Special Interest Group on Knowledge Discovery in Data","SIGMOD ACM Special Interest Group on Management of Data"]},"container-title":["Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3711896.3737394","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T18:01:02Z","timestamp":1777572062000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3711896.3737394"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,3]]},"references-count":95,"alternative-id":["10.1145\/3711896.3737394","10.1145\/3711896"],"URL":"https:\/\/doi.org\/10.1145\/3711896.3737394","relation":{},"subject":[],"published":{"date-parts":[[2025,8,3]]},"assertion":[{"value":"2025-08-03","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}