{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,23]],"date-time":"2026-01-23T07:59:26Z","timestamp":1769155166564,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":52,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,7,13]],"date-time":"2024-07-13T00:00:00Z","timestamp":1720828800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/501100000038","name":"Natural Sciences and Engineering Research Council of Canada","doi-asserted-by":"publisher","award":["RGPIN-2020-05375"],"award-info":[{"award-number":["RGPIN-2020-05375"]}],"id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/501100000038","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,7,13]]},"DOI":"10.1145\/3641519.3657523","type":"proceedings-article","created":{"date-parts":[[2024,7,12]],"date-time":"2024-07-12T10:39:28Z","timestamp":1720780768000},"page":"1-11","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Scale-Invariant Monocular Depth Estimation via SSI Depth"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9845-7866","authenticated-orcid":false,"given":"S. Mahdi","family":"H. Miangoleh","sequence":"first","affiliation":[{"name":"Simon Fraser University, Canada"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5645-4931","authenticated-orcid":false,"given":"Mahesh","family":"Reddy","sequence":"additional","affiliation":[{"name":"Simon Fraser University, Canada"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1495-0491","authenticated-orcid":false,"given":"Ya\u011f\u0131z","family":"Aksoy","sequence":"additional","affiliation":[{"name":"Simon Fraser University, Canada"}]}],"member":"320","published-online":{"date-parts":[[2024,7,13]]},"reference":[{"key":"e_1_3_2_2_1_1","volume-title":"Proc. CVPR.","author":"Bhat Shariq\u00a0Farooq","year":"2021","unstructured":"Shariq\u00a0Farooq Bhat, Ibraheem Alhashim, and Peter Wonka. 2021. Adabins: Depth estimation using adaptive bins. In Proc. CVPR."},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19769-7_28"},{"key":"e_1_3_2_2_3_1","volume-title":"ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depth. arXiv:2302.12288 [cs.CV]","author":"Bhat Shariq\u00a0Farooq","year":"2023","unstructured":"Shariq\u00a0Farooq Bhat, Reiner Birkl, Diana Wofk, Peter Wonka, and Matthias M\u00fcller. 2023. ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depth. arXiv:2302.12288 [cs.CV] (2023)."},{"key":"e_1_3_2_2_4_1","volume-title":"Proc. NeurIPS.","author":"Chen Weifeng","year":"2016","unstructured":"Weifeng Chen, Zhao Fu, Dawei Yang, and Jia Deng. 2016. Single-image depth perception in the wild. In Proc. NeurIPS."},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00575"},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.173"},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/98"},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"e_1_3_2_2_9_1","volume-title":"A large dataset of object scans. arXiv:1602.02481 [cs.CV]","author":"Choi Sungjoon","year":"2016","unstructured":"Sungjoon Choi, Qian-Yi Zhou, Stephen Miller, and Vladlen Koltun. 2016. A large dataset of object scans. arXiv:1602.02481 [cs.CV] (2016)."},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01061"},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.304"},{"key":"e_1_3_2_2_12_1","volume-title":"Proc. NeurIPS.","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. In Proc. NeurIPS."},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00214"},{"key":"e_1_3_2_2_14_1","volume":"201","author":"Godard Cl\u00e9ment","unstructured":"Cl\u00e9ment Godard, Oisin Mac\u00a0Aodha, and Gabriel\u00a0J Brostow. 2017. Unsupervised monocular depth estimation with left-right consistency. In Proc. CVPR.","journal-title":"J Brostow."},{"key":"e_1_3_2_2_15_1","volume-title":"Proc. CVPR Workshops.","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. In Proc. CVPR Workshops."},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20086-1_2"},{"key":"e_1_3_2_2_17_1","volume-title":"Proc. ECCV Workshops.","author":"Koch Tobias","year":"2018","unstructured":"Tobias Koch, Lukas Liebel, Friedrich Fraundorfer, and Marco Korner. 2018. Evaluation of CNN-based single-image depth estimation methods. In Proc. ECCV Workshops."},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00312"},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00996"},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00955"},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00465"},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00218"},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00711"},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_12"},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00956"},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"crossref","unstructured":"Simon Niklaus Long Mai Jimei Yang and Feng Liu. 2019. 3D Ken Burns effect from a single image. ACM Trans. Graph. (2019).","DOI":"10.1145\/3355089.3356528"},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01580"},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01466"},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01196"},{"key":"e_1_3_2_2_30_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 Trans. Pattern Anal. Mach. Intell. (2020)."},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01073"},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-11752-2_3"},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00805"},{"key":"e_1_3_2_2_34_1","volume-title":"The Replica dataset: A digital replica of indoor spaces. arXiv:1906.05797 [cs.CV]","author":"Straub Julian","year":"2019","unstructured":"Julian Straub, Thomas Whelan, Lingni Ma, Yufan Chen, Erik Wijmans, Simon Green, Jakob\u00a0J Engel, Raul Mur-Artal, Carl Ren, Shobhit Verma, 2019. The Replica dataset: A digital replica of indoor spaces. arXiv:1906.05797 [cs.CV] (2019)."},{"key":"e_1_3_2_2_35_1","volume-title":"Proc. ICML.","author":"Tan Mingxing","year":"2019","unstructured":"Mingxing Tan and Quoc Le. 2019. Efficientnet: Rethinking model scaling for convolutional neural networks. In Proc. ICML."},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_24"},{"key":"e_1_3_2_2_37_1","volume-title":"Diode: A dense indoor and outdoor depth dataset. arXiv:1908.00463 [cs.CV]","author":"Vasiljevic Igor","year":"2019","unstructured":"Igor Vasiljevic, Nick Kolkin, Shanyi Zhang, Ruotian Luo, Haochen Wang, Falcon\u00a0Z Dai, Andrea\u00a0F Daniele, Mohammadreza Mostajabi, Steven Basart, Matthew\u00a0R Walter, 2019. Diode: A dense indoor and outdoor depth dataset. arXiv:1908.00463 [cs.CV] (2019)."},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"crossref","unstructured":"Neal Wadhwa Rahul Garg David\u00a0E Jacobs Bryan\u00a0E Feldman Nori Kanazawa Robert Carroll Yair Movshovitz-Attias Jonathan\u00a0T Barron Yael Pritch and Marc Levoy. 2018. Synthetic depth-of-field with a single-camera mobile phone. ACM Trans. Graph. (2018).","DOI":"10.1145\/3197517.3201329"},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58558-7_19"},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341801"},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00579"},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00040"},{"key":"e_1_3_2_2_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00069"},{"key":"e_1_3_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"e_1_3_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00987"},{"key":"e_1_3_2_2_46_1","volume-title":"Virtual Normal: Enforcing Geometric Constraints for Accurate and Robust Depth Prediction","author":"Yin Wei","year":"2021","unstructured":"Wei Yin, Yifan Liu, and Chunhua Shen. 2021a. Virtual Normal: Enforcing Geometric Constraints for Accurate and Robust Depth Prediction. IEEE Trans. Pattern Anal. Mach. Intell. (2021)."},{"key":"e_1_3_2_2_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00578"},{"key":"e_1_3_2_2_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00830"},{"key":"e_1_3_2_2_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00027"},{"key":"e_1_3_2_2_50_1","volume-title":"Proc. CVPR.","author":"Yuan Weihao","year":"2022","unstructured":"Weihao Yuan, Xiaodong Gu, Zuozhuo Dai, Siyu Zhu, and Ping Tan. 2022. NeWCRFs: Neural Window Fully-connected CRFs for Monocular Depth Estimation. In Proc. CVPR."},{"key":"e_1_3_2_2_51_1","volume-title":"Proc. ECCV.","author":"Zheng Chuanxia","year":"2018","unstructured":"Chuanxia Zheng, Tat-Jen Cham, and Jianfei Cai. 2018. T2net: Synthetic-to-realistic translation for solving single-image depth estimation tasks. In Proc. ECCV."},{"key":"e_1_3_2_2_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.52"}],"event":{"name":"SIGGRAPH '24: Special Interest Group on Computer Graphics and Interactive Techniques Conference","location":"Denver CO USA","acronym":"SIGGRAPH '24","sponsor":["SIGGRAPH ACM Special Interest Group on Computer Graphics and Interactive Techniques"]},"container-title":["Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3641519.3657523","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3641519.3657523","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:05:50Z","timestamp":1750291550000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3641519.3657523"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,13]]},"references-count":52,"alternative-id":["10.1145\/3641519.3657523","10.1145\/3641519"],"URL":"https:\/\/doi.org\/10.1145\/3641519.3657523","relation":{},"subject":[],"published":{"date-parts":[[2024,7,13]]},"assertion":[{"value":"2024-07-13","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}