{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,3]],"date-time":"2026-10-03T17:27:27Z","timestamp":1791048447699,"version":"4.1.0"},"reference-count":55,"publisher":"Association for Computing Machinery (ACM)","issue":"12","license":[{"start":{"date-parts":[[2024,11,18]],"date-time":"2024-11-18T00:00:00Z","timestamp":1731888000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Multimedia Comput. Commun. Appl."],"published-print":{"date-parts":[[2024,12,31]]},"abstract":"<jats:p>Estimating the depth of transparent objects is one of the well-known challenges of RGB-D cameras due to the reflection and refraction effects. Previously, researchers propose to correct the depth of transparent objects by using their estimated segmentation masks because it is possible to recover the internal depth of an object just from its boundary, as illustrated by those depth-from-silhouette methods. However, these algorithms only use segmentation masks. They ignore the internal structure information from the mask segmentation features, which we argue are more useful for transparent depth estimation. In this work, we demonstrate the effectiveness of segmentation features for transparent object depth estimation. We show that it is even possible to recover the depth map just from segmentation features, without any RGB or depth map as input. Based on this observation, we propose DualTransNet which uses segmentation features for transparent depth completion. In our DualTransNet, we feed segmentation features from an extra module to the main network for better depth completion quality. Extensive experiments have shown the superiority of segmentation features as well as the state-of-the-art performance of our network.<\/jats:p>","DOI":"10.1145\/3694978","type":"journal-article","created":{"date-parts":[[2024,9,9]],"date-time":"2024-09-09T17:06:47Z","timestamp":1725901607000},"page":"1-19","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":12,"title":["Transparent Depth Completion Using Segmentation Features"],"prefix":"10.1145","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-5695-2835","authenticated-orcid":false,"given":"Boqian","family":"Liu","sequence":"first","affiliation":[{"name":"Dalian University of Technology, Dalian, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3882-2205","authenticated-orcid":false,"given":"Haojie","family":"Li","sequence":"additional","affiliation":[{"name":"Shandong University of Science and Technology, Qingdao, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5011-9726","authenticated-orcid":false,"given":"Zhihui","family":"Wang","sequence":"additional","affiliation":[{"name":"Dalian University of Technology, Dalian, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5031-6618","authenticated-orcid":false,"given":"Tianfan","family":"Xue","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong, Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,11,18]]},"reference":[{"key":"e_1_3_1_2_2","doi-asserted-by":"publisher","DOI":"10.1145\/3597612"},{"key":"e_1_3_1_3_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3254650"},{"key":"e_1_3_1_4_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160537"},{"key":"e_1_3_1_5_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2699184"},{"key":"e_1_3_1_6_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_49"},{"key":"e_1_3_1_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3359190"},{"key":"e_1_3_1_8_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20074-8_22"},{"key":"e_1_3_1_9_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19842-7_22"},{"key":"e_1_3_1_10_2","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3183256"},{"key":"e_1_3_1_11_2","doi-asserted-by":"publisher","DOI":"10.1145\/3656476"},{"key":"e_1_3_1_12_2","doi-asserted-by":"crossref","unstructured":"Hao He Xiangtai Li Guangliang Cheng Jianping Shi Yunhai Tong Gaofeng Meng V\u00e9ronique Prinet and Lubin Weng. 2021. Enhanced Boundary Learning for Glass-like Object Segmentation. arXiv:2103.15734. Retrieved from https:\/\/arxiv.org\/abs\/2103.15734","DOI":"10.1109\/ICCV48922.2021.01556"},{"key":"e_1_3_1_13_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"e_1_3_1_14_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"e_1_3_1_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3191231"},{"key":"e_1_3_1_16_2","first-page":"8599","volume-title":"Proceedings of the 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR \u201920)","author":"Kalra Agastya","year":"2020","unstructured":"Agastya Kalra, Vage Taamazyan, Supreeth Krishna Rao, Kartik Venkataraman, Ramesh Raskar, and Achuta Kadambi. 2020. Deep Polarization Cues for Transparent Object Segmentation. In Proceedings of the 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR \u201920), 8599\u20138608. https:\/\/doi.org\/10.1109\/CVPR42600.2020.00863"},{"key":"e_1_3_1_17_2","unstructured":"Diederik P. Kingma and Jimmy Ba. 2014. Adam: A Method for Stochastic Optimization. arXiv:1412.6980. Retrieved from https:\/\/arxiv.org\/abs\/1412.6980"},{"key":"e_1_3_1_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2019.00103"},{"key":"e_1_3_1_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3300544"},{"key":"e_1_3_1_20_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01321"},{"key":"e_1_3_1_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2537337"},{"key":"e_1_3_1_22_2","doi-asserted-by":"publisher","DOI":"10.1145\/3638559"},{"key":"e_1_3_1_23_2","doi-asserted-by":"publisher","DOI":"10.1109\/iccv48922.2021.00986"},{"key":"e_1_3_1_24_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"e_1_3_1_25_2","unstructured":"Ilya Loshchilov and Frank Hutter. 2019. Decoupled Weight Decay Regularization. In Proceedings of 7th International Conference on Learning Representations ICLR. OpenReview.net New Orleans LA. Retrieved from https:\/\/openreview.net\/forum?id=Bkg6RiCqY7"},{"key":"e_1_3_1_26_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.359"},{"key":"e_1_3_1_27_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00374"},{"key":"e_1_3_1_28_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2023.103914"},{"key":"e_1_3_1_29_2","doi-asserted-by":"publisher","DOI":"10.1145\/3503250"},{"key":"e_1_3_1_30_2","doi-asserted-by":"publisher","DOI":"10.1145\/3663570"},{"key":"e_1_3_1_31_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"e_1_3_1_32_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197518"},{"key":"e_1_3_1_33_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3254665"},{"key":"e_1_3_1_34_2","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636382"},{"issue":"2","key":"e_1_3_1_35_2","doi-asserted-by":"crossref","first-page":"177","DOI":"10.1109\/LRA.2018.2884765","article-title":"Distinguishing Refracted Features Using Light Field Cameras with Application to Structure from Motion","volume":"4","author":"Tsai Dorian","year":"2018","unstructured":"Dorian Tsai, Donald G. Dansereau, Thierry Peynot, and Peter Corke. 2018. Distinguishing Refracted Features Using Light Field Cameras with Application to Structure from Motion. IEEE Robotics and Automation Letters 4, 2 (2018), 177\u2013184.","journal-title":"IEEE Robotics and Automation Letters"},{"key":"e_1_3_1_36_2","unstructured":"Avinash Ummadisingu Jongkeum Choi Koki Yamane Shimpei Masuda Naoki Fukaya and Kuniyuki Takahashi. 2024. SAID-NeRF: Segmentation-AIDed NeRF for Depth Completion of Transparent Objects. arXiv:2403.19607. Retrieved from https:\/\/arxiv.org\/abs\/2403.19607"},{"key":"e_1_3_1_37_2","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2018.00163"},{"key":"e_1_3_1_38_2","doi-asserted-by":"publisher","DOI":"10.1145\/3624747"},{"key":"e_1_3_1_39_2","doi-asserted-by":"publisher","DOI":"10.1145\/3506708"},{"key":"e_1_3_1_40_2","doi-asserted-by":"publisher","DOI":"10.1364\/OE.416130"},{"key":"e_1_3_1_41_2","first-page":"696","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Xie Enze","year":"2020","unstructured":"Enze Xie, Wenjia Wang, Wenhai Wang, Mingyu Ding, Chunhua Shen, and Ping Luo. 2020. Segmenting Transparent Objects in the Wild. In Computer Vision \u2013 ECCV 2020, Andrea Vedaldi, Horst Bischof, Thomas Brox, and Jan-Michael Frahm (Eds.), Springer International Publishing, Cham, 696\u2013711."},{"key":"e_1_3_1_42_2","first-page":"1045","volume-title":"Proceedings of the International Joint Conference on Artificial Intelligence","author":"Xie E.","year":"2021","unstructured":"E. Xie, W. J. Wang, W. H. Wang, P. Sun, H. Xu, D. Liang, and P. Luo. 2021. Segmenting Transparent Objects in the Wild with Transformer. In Proceedings of the International Joint Conference on Artificial Intelligence, 1045\u20130823."},{"key":"e_1_3_1_43_2","first-page":"827","volume-title":"Proceedings of the 5th Conference on Robot Learning","volume":"164","author":"Xu Haoping","year":"2022","unstructured":"Haoping Xu, Yi Ru Wang, Sagi Eppel, Alan Aspuru-Guzik, Florian Shkurti, and Animesh Garg. 2022. Seeing Glass: Joint Point-Cloud and Depth Completion for Transparent Objects. In Proceedings of the 5th Conference on Robot Learning, Vol. 164. Aleksandra Faust, David Hsu, and Gerhard Neumann (Eds.), PMLR, 827\u2013838. DOI: https:\/\/proceedings.mlr.press\/v164\/xu22b.html"},{"key":"e_1_3_1_44_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.393"},{"key":"e_1_3_1_45_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCI.2019.2893820"},{"key":"e_1_3_1_46_2","doi-asserted-by":"publisher","DOI":"10.1145\/3471870"},{"key":"e_1_3_1_47_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.75"},{"key":"e_1_3_1_48_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3162709"},{"key":"e_1_3_1_49_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2023.3297791"},{"key":"e_1_3_1_50_2","doi-asserted-by":"publisher","DOI":"10.3389\/fnbot.2022.1041702"},{"issue":"1","key":"e_1_3_1_51_2","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/TASE.2024.3371583","article-title":"TCRNet: Transparent Object Depth Completion with Cascade Refinements","volume":"21","author":"Zhai Di-Hua","year":"2024","unstructured":"Di-Hua Zhai, Sheng Yu, Wei Wang, Yuyin Guan, and Yuanqing Xia. 2024. TCRNet: Transparent Object Depth Completion with Cascade Refinements. IEEE Transactions on Automation Science and Engineering 21, 1 (2024), 1\u201320.","journal-title":"IEEE Transactions on Automation Science and Engineering"},{"key":"e_1_3_1_52_2","first-page":"175","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Zhang Yinda","year":"2018","unstructured":"Yinda Zhang and Thomas Funkhouser. 2018. Deep Depth Completion of a Single RGB-D Image. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 175\u2013185."},{"key":"e_1_3_1_53_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3378918"},{"key":"e_1_3_1_54_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.660"},{"key":"e_1_3_1_55_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00462"},{"key":"e_1_3_1_56_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00596"}],"container-title":["ACM Transactions on Multimedia Computing, Communications, and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3694978","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3694978","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:18:07Z","timestamp":1750295887000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3694978"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,18]]},"references-count":55,"journal-issue":{"issue":"12","published-print":{"date-parts":[[2024,12,31]]}},"alternative-id":["10.1145\/3694978"],"URL":"https:\/\/doi.org\/10.1145\/3694978","relation":{},"ISSN":["1551-6857","1551-6865"],"issn-type":[{"value":"1551-6857","type":"print"},{"value":"1551-6865","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,18]]},"assertion":[{"value":"2024-05-14","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-08-21","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-11-18","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}