{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,28]],"date-time":"2026-06-28T10:52:25Z","timestamp":1782643945313,"version":"3.54.5"},"reference-count":34,"publisher":"MDPI AG","issue":"19","license":[{"start":{"date-parts":[[2022,9,28]],"date-time":"2022-09-28T00:00:00Z","timestamp":1664323200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Center for Applied Research in Artificial Intelligence (CARAI)","award":["UD190031RD"],"award-info":[{"award-number":["UD190031RD"]}]},{"name":"Center for Applied Research in Artificial Intelligence (CARAI)","award":["NRF-2022R1F1A1074908"],"award-info":[{"award-number":["NRF-2022R1F1A1074908"]}]},{"name":"Center for Applied Research in Artificial Intelligence (CARAI)","award":["2020-0-01450"],"award-info":[{"award-number":["2020-0-01450"]}]},{"name":"Center for Applied Research in Artificial Intelligence (CARAI)","award":["NRF-2021R1A4A1032580"],"award-info":[{"award-number":["NRF-2021R1A4A1032580"]}]},{"name":"National Research Foundation of Korea (NRF)","award":["UD190031RD"],"award-info":[{"award-number":["UD190031RD"]}]},{"name":"National Research Foundation of Korea (NRF)","award":["NRF-2022R1F1A1074908"],"award-info":[{"award-number":["NRF-2022R1F1A1074908"]}]},{"name":"National Research Foundation of Korea (NRF)","award":["2020-0-01450"],"award-info":[{"award-number":["2020-0-01450"]}]},{"name":"National Research Foundation of Korea (NRF)","award":["NRF-2021R1A4A1032580"],"award-info":[{"award-number":["NRF-2021R1A4A1032580"]}]},{"name":"Institute of Information &amp; communications Technology Planning &amp; Evaluation (IITP)","award":["UD190031RD"],"award-info":[{"award-number":["UD190031RD"]}]},{"name":"Institute of Information &amp; communications Technology Planning &amp; Evaluation (IITP)","award":["NRF-2022R1F1A1074908"],"award-info":[{"award-number":["NRF-2022R1F1A1074908"]}]},{"name":"Institute of Information &amp; communications Technology Planning &amp; Evaluation (IITP)","award":["2020-0-01450"],"award-info":[{"award-number":["2020-0-01450"]}]},{"name":"Institute of Information &amp; communications Technology Planning &amp; Evaluation (IITP)","award":["NRF-2021R1A4A1032580"],"award-info":[{"award-number":["NRF-2021R1A4A1032580"]}]},{"name":"National Research Foundation of Korea (NRF)","award":["UD190031RD"],"award-info":[{"award-number":["UD190031RD"]}]},{"name":"National Research Foundation of Korea (NRF)","award":["NRF-2022R1F1A1074908"],"award-info":[{"award-number":["NRF-2022R1F1A1074908"]}]},{"name":"National Research Foundation of Korea (NRF)","award":["2020-0-01450"],"award-info":[{"award-number":["2020-0-01450"]}]},{"name":"National Research Foundation of Korea (NRF)","award":["NRF-2021R1A4A1032580"],"award-info":[{"award-number":["NRF-2021R1A4A1032580"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Depth perception capability is one of the essential requirements for various autonomous driving platforms. However, accurate depth estimation in a real-world setting is still a challenging problem due to high computational costs. In this paper, we propose a lightweight depth completion network for depth perception in real-world environments. To effectively transfer a teacher\u2019s knowledge, useful for the depth completion, we introduce local similarity-preserving knowledge distillation (LSPKD), which allows similarities between local neighbors to be transferred during the distillation. With our LSPKD, a lightweight student network is precisely guided by a heavy teacher network, regardless of the density of the ground-truth data. Experimental results demonstrate that our method is effective to reduce computational costs during both training and inference stages while achieving superior performance over other lightweight networks.<\/jats:p>","DOI":"10.3390\/s22197388","type":"journal-article","created":{"date-parts":[[2022,9,29]],"date-time":"2022-09-29T01:23:16Z","timestamp":1664414596000},"page":"7388","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":12,"title":["Lightweight Depth Completion Network with Local Similarity-Preserving Knowledge Distillation"],"prefix":"10.3390","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9126-9061","authenticated-orcid":false,"given":"Yongseop","family":"Jeong","sequence":"first","affiliation":[{"name":"The Robotics Program, Korea Advanced Institute of Science and Technology, 291 Daehak-ro, Yuseong-gu, Daejeon 34141, Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2296-819X","authenticated-orcid":false,"given":"Jinsun","family":"Park","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Pusan National University, 2 Busandaehak-ro 63beon-gil, Geumjeong-gu, Busan 46241, Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2184-921X","authenticated-orcid":false,"given":"Donghyeon","family":"Cho","sequence":"additional","affiliation":[{"name":"Department of Electronics Engineering, Chungnam National University, 99 Daehak-ro, Yuseong-gu, Daejeon 34134, Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0190-7443","authenticated-orcid":false,"given":"Yoonjin","family":"Hwang","sequence":"additional","affiliation":[{"name":"Department of Mechanical Engineering, Korea Advanced Institute of Science and Technology, 291 Daehak-ro, Yuseong-gu, Daejeon 34141, Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8555-4429","authenticated-orcid":false,"given":"Seibum B.","family":"Choi","sequence":"additional","affiliation":[{"name":"Department of Mechanical Engineering, Korea Advanced Institute of Science and Technology, 291 Daehak-ro, Yuseong-gu, Daejeon 34141, Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9626-5983","authenticated-orcid":false,"given":"In So","family":"Kweon","sequence":"additional","affiliation":[{"name":"School of Electrical Engineering, Korea Advanced Institute of Science and Technology, 291 Daehak-ro, Yuseong-gu, Daejeon 34141, Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2022,9,28]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Ettinger, S., Cheng, S., Caine, B., Liu, C., Zhao, H., Pradhan, S., Chai, Y., Sapp, B., Qi, C.R., and Zhou, Y. (2021, January 10\u201317). Large Scale Interactive Motion Forecasting for Autonomous Driving: The Waymo Open Motion Dataset. Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), Montreal, QC, Canada.","DOI":"10.1109\/ICCV48922.2021.00957"},{"key":"ref_2","unstructured":"Wilson, B., Qi, W., Agarwal, T., Lambert, J., Singh, J., Khandelwal, S., Pan, B., Kumar, R., Hartnett, A., and Pontes, J.K. (2021, January 6\u201314). Argoverse 2: Next Generation Datasets for Self-Driving Perception and Forecasting. Proceedings of the Thirty-Fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 2), Virtual Event. Available online: https:\/\/nips.cc\/Conferences\/2021."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Geiger, A., Lenz, P., and Urtasun, R. (2012, January 16\u201321). Are we ready for autonomous driving? The kitti vision benchmark suite. Proceedings of the Computer Vision and Pattern Recognition (CVPR), Providence, RI, USA.","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"3795","DOI":"10.1109\/LRA.2022.3148457","article-title":"Panoptic nuscenes: A large-scale benchmark for lidar panoptic segmentation and tracking","volume":"7","author":"Fong","year":"2022","journal-title":"IEEE Robot. Autom. Lett."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Malawade, A.V., Mortlock, T., and Al Faruque, M.A. (2022, January 4\u20136). HydraFusion: Context-Aware Selective Sensor Fusion for Robust and Efficient Autonomous Vehicle Perception. Proceedings of the 2022 ACM\/IEEE 13th International Conference on Cyber-Physical Systems (ICCPS), Milano, Italy.","DOI":"10.1109\/ICCPS54341.2022.00013"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Zheng, W., Tang, W., Jiang, L., and Fu, C.W. (2021, January 20\u201325). SE-SSD: Self-Ensembling Single-Stage Object Detector from Point Cloud. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, TN, USA.","DOI":"10.1109\/CVPR46437.2021.01426"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Chen, Q., Wang, Y., Yang, T., Zhang, X., Cheng, J., and Sun, J. (2021, January 20\u201325). You Only Look One-Level Feature. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, TN, USA.","DOI":"10.1109\/CVPR46437.2021.01284"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Ma, F., and Karaman, S. (2018, January 21\u201325). Sparse-to-dense: Depth prediction from sparse depth samples and a single image. Proceedings of the IEEE International Conference on Robotics and Automation (ICRA), Brisbane, Australia.","DOI":"10.1109\/ICRA.2018.8460184"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Cheng, X., Wang, P., and Yang, R. (2018, January 8\u201314). Depth estimation via affinity learned with convolutional spatial propagation network. Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany.","DOI":"10.1007\/978-3-030-01270-0_7"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Park, J., Joo, K., Hu, Z., Liu, C.K., and Kweon, I.S. (2020, January 23\u201328). Non-Local Spatial Propagation Network for Depth Completion. Proceedings of the European Conference on Computer Vision (ECCV), Glasgow, UK.","DOI":"10.1007\/978-3-030-58601-0_8"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"1615","DOI":"10.1109\/LSP.2021.3092280","article-title":"Dilated U-block for lightweight indoor depth completion with sobel edge","volume":"28","author":"Tao","year":"2021","journal-title":"IEEE Signal Process. Lett."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"1619","DOI":"10.1007\/s00371-021-02092-8","article-title":"Attention Unet++ for lightweight depth estimation from sparse depth samples and a single RGB image","volume":"38","author":"Zhao","year":"2022","journal-title":"Vis. Comput."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1109\/LSP.2020.2975426","article-title":"Integral knowledge distillation for multi-person pose estimation","volume":"27","author":"Xu","year":"2020","journal-title":"IEEE Signal Process. Lett."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"1320","DOI":"10.1109\/LSP.2020.3011326","article-title":"Progressive Motion Representation Distillation With Two-Branch Networks for Egocentric Activity Recognition","volume":"27","author":"Liu","year":"2020","journal-title":"IEEE Signal Process. Lett."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"2139","DOI":"10.1109\/LSP.2020.3039952","article-title":"Lightweight deep cnn for natural image matting via similarity-preserving knowledge distillation","volume":"27","author":"Yoon","year":"2020","journal-title":"IEEE Signal Process. Lett."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Yang, C., Zhou, H., An, Z., Jiang, X., Xu, Y., and Zhang, Q. (2022, January 19\u201324). Cross-image relational knowledge distillation for semantic segmentation. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, New Orleans, LA, USA.","DOI":"10.1109\/CVPR52688.2022.01200"},{"key":"ref_17","unstructured":"Tung, F., and Mori, G. (November, January 27). Similarity-preserving knowledge distillation. Proceedings of the International Conference on Computer Vision (ICCV), Seoul, Korea."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Qu, C., Nguyen, T., and Taylor, C. (2020, January 1\u20137). Depth Completion via Deep Basis Fitting. Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV), Snowmass Village, CO, USA.","DOI":"10.1109\/WACV45572.2020.9093349"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Hu, J., Bao, C., Ozay, M., Fan, C., Gao, Q., Liu, H., and Lam, T.L. (2022). Deep Depth Completion from Extremely Sparse Data: A Survey. arXiv.","DOI":"10.1109\/TPAMI.2022.3229090"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Chen, L., and Li, Q. (2022). An Adaptive Fusion Algorithm for Depth Completion. Sensors, 22.","DOI":"10.3390\/s22124603"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Lee, B.U., Jeon, H.G., Im, S., and Kweon, I.S. (2019, January 20\u201324). Depth completion with deep geometry and context guidance. Proceedings of the IEEE International Conference on Robotics and Automation (ICRA), Montreal, QC, Canada.","DOI":"10.1109\/ICRA.2019.8794161"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Lee, B.U., Lee, K., and Kweon, I.S. (2021, January 20\u201325). Depth Completion using Plane-Residual Representation. Proceedings of the Computer Vision and Pattern Recognition (CVPR), Nashville, TN, USA.","DOI":"10.1109\/CVPR46437.2021.01370"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27\u201330). Deep residual learning for image recognition. Proceedings of the Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref_24","unstructured":"Hinton, G., Vinyals, O., and Dean, J. (2015, January 11\u201312). Distilling the Knowledge in a Neural Network. Proceedings of the Neural Information Processing Systems Workshops (NeurIPSW), Montreal, QC, Canada."},{"key":"ref_25","unstructured":"Romero, A., Ballas, N., Kahou, S.E., Chassang, A., Gatta, C., and Bengio, Y. (2015, January 7\u20139). Fitnets: Hints for thin deep nets. Proceedings of the International Conference on Learning Representations, San Diego, CA, USA."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"228","DOI":"10.1109\/TPAMI.2007.1177","article-title":"A closed-form solution to natural image matting","volume":"30","author":"Levin","year":"2007","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_27","first-page":"1521","article-title":"Learning affinity via spatial propagation networks","volume":"2017","author":"Liu","year":"2017","journal-title":"Proc. Adv. Neural Inf. Process. Syst."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Silberman, N., Hoiem, D., Kohli, P., and Fergus, R. (2012, January 7\u201313). Indoor Segmentation and Support Inference from RGBD Images. Proceedings of the European Conference on Computer Vision (ECCV), Florence, Italy.","DOI":"10.1007\/978-3-642-33715-4_54"},{"key":"ref_29","first-page":"8026","article-title":"Pytorch: An imperative style, high-performance deep learning library","volume":"32","author":"Paszke","year":"2019","journal-title":"Proc. Adv. Neural Inf. Process. Syst."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Passalis, N., and Tefas, A. (2018, January 8\u201314). Learning deep representations with probabilistic knowledge transfer. Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany.","DOI":"10.1007\/978-3-030-01252-6_17"},{"key":"ref_31","unstructured":"Zagoruyko, S., and Komodakis, N. (2017, January 24\u201326). Paying more attention to attention: Improving the performance of convolutional neural networks via attention transfer. Proceedings of the International Conference on Learning Representations, Toulon, France."},{"key":"ref_32","unstructured":"Uhrig, J., Schneider, N., Schneider, L., Franke, U., Brox, T., and Geiger, A. (, January 10\u201312). Sparsity invariant cnns. Proceedings of the International Conference on 3D Vision (3DV), Qingdao, China."},{"key":"ref_33","unstructured":"Ma, F., Cavalheiro, G.V., and Karaman, S. (, January 20\u201324). Self-supervised sparse-to-dense: Self-supervised depth completion from lidar and monocular camera. Proceedings of the IEEE International Conference on Robotics and Automation (ICRA), Montreal, QC, Canada."},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Qiu, J., Cui, Z., Zhang, Y., Zhang, X., Liu, S., Zeng, B., and Pollefeys, M. (2019, January 15\u201320). Deeplidar: Deep surface normal guided depth prediction for outdoor scene from sparse lidar data and single color image. Proceedings of the Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.00343"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/22\/19\/7388\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T00:41:22Z","timestamp":1760143282000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/22\/19\/7388"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,9,28]]},"references-count":34,"journal-issue":{"issue":"19","published-online":{"date-parts":[[2022,10]]}},"alternative-id":["s22197388"],"URL":"https:\/\/doi.org\/10.3390\/s22197388","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,9,28]]}}}