{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,6]],"date-time":"2026-01-06T08:57:41Z","timestamp":1767689861141,"version":"3.48.0"},"reference-count":62,"publisher":"MDPI AG","issue":"1","license":[{"start":{"date-parts":[[2026,1,4]],"date-time":"2026-01-04T00:00:00Z","timestamp":1767484800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Guangdong Province Special Fund for Science and Technology","award":["STKJ202209017"],"award-info":[{"award-number":["STKJ202209017"]}]},{"name":"Guangdong Science and Technology Plan Projects","award":["STKJ2023012"],"award-info":[{"award-number":["STKJ2023012"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Computers"],"abstract":"<jats:p>For UAVs, the industry currently relies on expensive sensors for obstacle avoidance. A significant challenge arises from the scarcity of high-quality depth estimation datasets tailored for low-altitude environments, which hinders the advancement of self-supervised learning methods in these settings. Furthermore, mainstream depth estimation models capable of achieving obstacle avoidance through image recognition are built upon convolutional neural networks or hybrid Transformers. Their high computational costs make deployment on resource-constrained edge devices challenging. While existing lightweight convolutional networks reduce parameter counts, they struggle to simultaneously capture essential features and fine details in complex scenes. In this work, we introduce LFP-Mono as a lightweight self-supervised monocular depth estimation network. In the paper, we will detail the Pooling Convolution Downsampling (PCD) module, Continuously Dilated and Weighted Convolution (CDWC) module, and Cross-level Feature Integration (CFI) module. All results show that LFP-Mono outperforms existing lightweight methods on the KITTI benchmark, and by evaluating with the Make3D dataset, show that our method generalizes outdoors. Finally, by training and testing on the Syndrone dataset, baseline work shows that LFP-Mono exceeds state-of-the-art methods for low-altitude drone performance.<\/jats:p>","DOI":"10.3390\/computers15010019","type":"journal-article","created":{"date-parts":[[2026,1,5]],"date-time":"2026-01-05T10:03:48Z","timestamp":1767607428000},"page":"19","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["LFP-Mono: Lightweight Self-Supervised Network Applying Monocular Depth Estimation to Low-Altitude Environment Scenarios"],"prefix":"10.3390","volume":"15","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9879-2960","authenticated-orcid":false,"given":"Hao","family":"Cai","sequence":"first","affiliation":[{"name":"College of Mathematics and Computer Science, Shantou University, Shantou 515063, China"},{"name":"Guangdong Provincial Key Laboratory of Frontier Mathematics and Large-Scale Model Computing in Higher Education Institutions, Shantou 515063, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-2697-6001","authenticated-orcid":false,"given":"Jiafu","family":"Liu","sequence":"additional","affiliation":[{"name":"College of Mathematics and Computer Science, Shantou University, Shantou 515063, China"},{"name":"Guangdong Provincial Key Laboratory of Frontier Mathematics and Large-Scale Model Computing in Higher Education Institutions, Shantou 515063, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinhong","family":"Zhang","sequence":"additional","affiliation":[{"name":"College of Mathematics and Computer Science, Shantou University, Shantou 515063, China"},{"name":"Guangdong Provincial Key Laboratory of Frontier Mathematics and Large-Scale Model Computing in Higher Education Institutions, Shantou 515063, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jingxuan","family":"Xu","sequence":"additional","affiliation":[{"name":"College of Mathematics and Computer Science, Shantou University, Shantou 515063, China"},{"name":"Guangdong Provincial Key Laboratory of Frontier Mathematics and Large-Scale Model Computing in Higher Education Institutions, Shantou 515063, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-7793-8474","authenticated-orcid":false,"given":"Yi","family":"Zhang","sequence":"additional","affiliation":[{"name":"College of Mathematics and Computer Science, Shantou University, Shantou 515063, China"},{"name":"Guangdong Provincial Key Laboratory of Frontier Mathematics and Large-Scale Model Computing in Higher Education Institutions, Shantou 515063, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qin","family":"Yang","sequence":"additional","affiliation":[{"name":"College of Mathematics and Computer Science, Shantou University, Shantou 515063, China"},{"name":"Guangdong Provincial Key Laboratory of Frontier Mathematics and Large-Scale Model Computing in Higher Education Institutions, Shantou 515063, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2026,1,4]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., and Zagoruyko, S. (2020, January 23\u201328). End-to-end object detection with transformers. Proceedings of the European Conference on Computer Vision, Virtual.","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Ramamonjisoa, M., Du, Y., and Lepetit, V. (2020, January 14\u201319). Predicting sharp and accurate occlusion boundaries in monocular depth estimation using displacement fields. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Virtual.","DOI":"10.1109\/CVPR42600.2020.01466"},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Laina, I., Rupprecht, C., Belagiannis, V., Tombari, F., and Navab, N. (2016, January 25\u201328). Deeper depth prediction with fully convolutional residual networks. Proceedings of the 2016 Fourth International Conference on 3D Vision, Stanford, CA, USA.","DOI":"10.1109\/3DV.2016.32"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Fu, H., Gong, M., Wang, C., Batmanghelich, K., and Tao, D. (2018, January 18\u201322). Deep ordinal regression network for monocular depth estimation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00214"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Zhou, T., Brown, M., Snavely, N., and Lowe, D.G. (2017, January 21\u201326). Unsupervised learning of depth and ego-motion from video. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.700"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Godard, C., Mac Aodha, O., and Brostow, G.J. (2017, January 21\u201326). Unsupervised monocular depth estimation with left-right consistency. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.699"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"1612","DOI":"10.1007\/s11431-020-1582-8","article-title":"Monocular depth estimation based on deep learning: An overview","volume":"63","author":"Zhao","year":"2020","journal-title":"Sci. China Technol. Sci."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Yin, Z., and Shi, J. (2018, January 18\u201322). Geonet: Unsupervised learning of dense depth, optical flow and camera pose. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00212"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Kumar, V.R., Klingner, M., Yogamani, S., Milz, S., Fingscheidt, T., and Mader, P. (2021, January 5\u20139). Syndistnet: Self-supervised monocular fisheye camera distance estimation synergized with semantic segmentation for autonomous driving. Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, Virtual.","DOI":"10.1109\/WACV48630.2021.00011"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Zhang, N., Nex, F., Vosselman, G., and Kerle, N. (2023, January 17\u201324). Lite-mono: A lightweight cnn and transformer architecture for self-supervised monocular depth estimation. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Vancouver, BC, Canada.","DOI":"10.1109\/CVPR52729.2023.01778"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Zhao, C., Zhang, Y., Poggi, M., Tosi, F., Guo, X., Zhu, Z., Huang, G., and Mattoccia, S. (2022, January 12\u201315). Monovit: Self-supervised monocular depth estimation with a vision transformer. Proceedings of the 2022 International Conference on 3D Vision, 3DV, Virtual.","DOI":"10.1109\/3DV57658.2022.00077"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Ranftl, R., Bochkovskiy, A., and Koltun, V. (2021, January 11\u201317). Vision transformers for dense prediction. Proceedings of the IEEE\/CVF International Conference on Computer Vision, Virtual.","DOI":"10.1109\/ICCV48922.2021.01196"},{"key":"ref_13","unstructured":"Godard, C., Mac Aodha, O., Firman, M., and Brostow, G.J. (November, January 27). Digging into self-supervised monocular depth estimation. Proceedings of the IEEE\/CVF International Conference on Computer Vision, Seoul, Republic of Korea."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"1231","DOI":"10.1177\/0278364913491297","article-title":"Vision meets robotics: The kitti dataset","volume":"32","author":"Geiger","year":"2013","journal-title":"Int. J. Robot. Res."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"824","DOI":"10.1109\/TPAMI.2008.132","article-title":"Make3d: Learning 3d scene structure from a single still image","volume":"31","author":"Saxena","year":"2008","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Rizzoli, G., Barbato, F., Caligiuri, M., and Zanuttigh, P. (2023, January 2\u20136). Syndrone-multi-modal uav dataset for urban scenarios. Proceedings of the IEEE\/CVF International Conference on Computer Vision, Paris, France.","DOI":"10.1109\/ICCVW60793.2023.00235"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Garg, R., Bg, V.K., Carneiro, G., and Reid, I. (2016, January 11\u201314). Unsupervised cnn for single view depth estimation: Geometry to the rescue. Proceedings of the European Conference on Computer Vision, Amsterdam, The Netherlands.","DOI":"10.1007\/978-3-319-46484-8_45"},{"key":"ref_18","unstructured":"Bian, J., Li, Z., Wang, N., Zhan, H., Shen, C., Cheng, M.M., and Reid, I. (2019). Unsupervised scale-consistent depth and ego-motion learning from monocular video. Advances in Neural Information Processing Systems."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Casser, V., Pirk, S., Mahjourian, R., and Angelova, A. (2019, January 16\u201320). Unsupervised monocular depth and ego-motion learning with structure and semantics. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops, Long Beach, CA, USA.","DOI":"10.1109\/CVPRW.2019.00051"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"114877","DOI":"10.1016\/j.eswa.2021.114877","article-title":"Deep monocular depth estimation leveraging a large-scale outdoor stereo dataset","volume":"178","author":"Cho","year":"2021","journal-title":"Expert Syst. Appl."},{"key":"ref_21","unstructured":"Chen, W., Fu, Z., Yang, D., and Deng, J. (2016). Single-image depth perception in the wild. Advances in Neural Information Processing Systems, The MIT Press."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Gur, S., and Wolf, L. (2019, January 16\u201320). Single image depth estimation trained via depth from defocus cues. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.00787"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"81","DOI":"10.1016\/j.neucom.2022.10.073","article-title":"GCNDepth: Self-supervised monocular depth estimation based on graph convolutional network","volume":"517","author":"Masoumian","year":"2023","journal-title":"Neurocomputing"},{"key":"ref_24","unstructured":"Eigen, D., Puhrsch, C., and Fergus, R. (2014, January 8\u201313). Depth map prediction from a single image using a multi-scale deep network. Proceedings of the Advances in Neural Information Processing Systems, Montreal, QC, Canada."},{"key":"ref_25","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., and Gelly, S. (2021, January 3\u20137). An Image is Worth 16 \u00d7 16 Words: Transformers for Image Recognition at Scale. Proceedings of the International Conference on Learning Representations, Virtual."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"14","DOI":"10.1016\/j.isprsjprs.2022.11.001","article-title":"Joint learning of frequency and spatial domains for dense image prediction","volume":"195","author":"Jia","year":"2023","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Hoiem, D., Efros, A.A., and Hebert, M. (August, January 31). Automatic photo pop-up. Proceedings of the ACM SIGGRAPH 2005, Los Angeles, CA, USA.","DOI":"10.1145\/1186822.1073232"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Cai, H., Li, J., Hu, M., Gan, C., and Han, S. (2023, January 2\u20136). Efficientvit: Lightweight multi-scale attention for high-resolution dense prediction. Proceedings of the IEEE\/CVF International Conference on Computer Vision, Paris, France.","DOI":"10.1109\/ICCV51070.2023.01587"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Varma, A., Chawla, H., Zonooz, B., and Arani, E. (2022). Transformers in self-supervised monocular depth estimation with unknown camera intrinsics. arXiv.","DOI":"10.5220\/0010884000003124"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Yang, L., Kang, B., Huang, Z., Xu, X., Feng, J., and Zhao, H. (2024, January 16\u201322). Depth anything: Unleashing the power of large-scale unlabeled data. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.","DOI":"10.1109\/CVPR52733.2024.00987"},{"key":"ref_31","first-page":"1502","article-title":"Self-supervised depth estimation leveraging global perception and geometric smoothness","volume":"24","author":"Jia","year":"2022","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"ref_32","unstructured":"Ali, A., Touvron, H., Caron, M., Bojanowski, P., Douze, M., Joulin, A., Laptev, I., Neverova, N., Synnaeve, G., and Verbeek, J. (2021, January 6\u201314). Xcit: Cross-covariance image transformers. Proceedings of the Advances in Neural Information Processing Systems, Virtual."},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Agarwal, A., and Arora, C. (2022). Depthformer: Multiscale vision transformer for monocular depth estimation with local global information fusion. arXiv.","DOI":"10.1109\/ICIP46576.2022.9897187"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"331","DOI":"10.1109\/TMRB.2022.3170206","article-title":"Self-supervised monocular depth estimation with 3-d displacement module for laparoscopic images","volume":"4","author":"Xu","year":"2022","journal-title":"IEEE Trans. Med. Robot. Bionics"},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Lyu, X., Liu, L., Wang, M., Kong, X., Liu, L., Liu, Y., Chen, X., and Yuan, Y. (2021, January 2\u20139). Hr-depth: High resolution self-supervised monocular depth estimation. Proceedings of the AAAI Conference on Artificial Intelligence, Virtual.","DOI":"10.1609\/aaai.v35i3.16329"},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Wofk, D., Ma, F., Yang, T.J., Karaman, S., and Sze, V. (2019, January 20\u201324). Fastdepth: Fast monocular depth estimation on embedded systems. Proceedings of the 2019 International Conference on Robotics and Automation, Montreal, QC, Canada.","DOI":"10.1109\/ICRA.2019.8794182"},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Yan, J., Zhao, H., Bu, P., and Jin, Y. (2021, January 1\u20133). Channel-wise attention-based network for self-supervised monocular depth estimation. Proceedings of the 2021 International Conference on 3D Vision, Virtual.","DOI":"10.1109\/3DV53792.2021.00056"},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Mehta, S., Rastegari, M., Shapiro, L., and Hajishirzi, H. (2019, January 16\u201320). Espnetv2: A light-weight, power efficient, and general purpose convolutional neural network. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.00941"},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Bae, J., Moon, S., and Im, S. (2023, January 7\u201314). Deep digging into the generalization of self-supervised monocular depth estimation. Proceedings of the AAAI Conference on Artificial Intelligence, Washington, DC, USA.","DOI":"10.1609\/aaai.v37i1.25090"},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Zhou, Z., Fan, X., Shi, P., and Xin, Y. (2021, January 11\u201317). R-msfm: Recurrent multi-scale feature modulation for monocular depth estimating. Proceedings of the IEEE\/CVF International Conference on Computer Vision, Virtual.","DOI":"10.1109\/ICCV48922.2021.01254"},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"113549","DOI":"10.1016\/j.asoc.2025.113549","article-title":"Striking a better balance between segmentation performance and computational costs with a minimalistic network design","volume":"182","author":"Dai","year":"2025","journal-title":"Appl. Soft Comput."},{"key":"ref_42","unstructured":"Chen, Y., Li, J., Xiao, H., Jin, X., Yan, S., and Feng, J. (2017). Dual path networks. Advances in Neural Information Processing Systems, The MIT Press."},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., and Wojna, Z. (2016, January 27\u201330). Rethinking the inception architecture for computer vision. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref_44","unstructured":"Yu, F., and Koltun, V. (2015). Multi-scale context aggregation by dilated convolutions. arXiv."},{"key":"ref_45","unstructured":"Cammarasana, S., and Patan\u00e8, G. (2025). Optimal Weighted Convolution for Classification and Denosing. arXiv."},{"key":"ref_46","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 IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref_47","unstructured":"Fernandez, A. (2024). TeLU Activation Function for Fast and Stable Deep Learning. [Master\u2019s Thesis, University of South Florida]."},{"key":"ref_48","unstructured":"Liu, S., Huang, D., and Wang, Y. (2019). Learning spatial fusion for single-shot object detection. arXiv."},{"key":"ref_49","doi-asserted-by":"crossref","unstructured":"Wang, G., Wang, K., and Lin, L. (2019, January 16\u201320). Adaptively connected neural networks. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.00188"},{"key":"ref_50","doi-asserted-by":"crossref","unstructured":"Woo, S., Park, J., Lee, J.Y., and Kweon, I.S. (2018, January 8\u201314). Cbam: Convolutional block attention module. Proceedings of the European Conference on Computer Vision, Munich, Germany.","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"ref_51","doi-asserted-by":"crossref","unstructured":"Fu, J., Liu, J., Tian, H., Li, Y., Bao, Y., Fang, Z., and Lu, H. (2019, January 16\u201320). Dual attention network for scene segmentation. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.00326"},{"key":"ref_52","unstructured":"Meng, W., Luo, Y., Li, X., Jiang, D., and Zhang, Z. (2025). PolaFormer: Polarity-aware linear attention for vision transformers. arXiv."},{"key":"ref_53","doi-asserted-by":"crossref","first-page":"104769","DOI":"10.1016\/j.dsp.2024.104769","article-title":"RTIA-Mono: Real-time lightweight self-supervised monocular depth estimation with global-local information aggregation","volume":"156","author":"Zhao","year":"2025","journal-title":"Digit. Signal Process."},{"key":"ref_54","doi-asserted-by":"crossref","first-page":"600","DOI":"10.1109\/TIP.2003.819861","article-title":"Image quality assessment: From error visibility to structural similarity","volume":"13","author":"Wang","year":"2004","journal-title":"IEEE Trans. Image Process."},{"key":"ref_55","doi-asserted-by":"crossref","unstructured":"Zhou, H., Greenwood, D., and Taylor, S. (2021). Self-supervised monocular depth estimation with internal feature fusion. arXiv.","DOI":"10.5244\/C.35.208"},{"key":"ref_56","doi-asserted-by":"crossref","unstructured":"Yang, N., Stumberg, L.V., Wang, R., and Cremers, D. (2020, January 14\u201319). D3vo: Deep depth, deep pose and deep uncertainty for monocular visual odometry. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Virtual.","DOI":"10.1109\/CVPR42600.2020.00136"},{"key":"ref_57","doi-asserted-by":"crossref","unstructured":"Wang, C., Buenaposada, J.M., Zhu, R., and Lucey, S. (2018, January 18\u201322). Learning depth from monocular videos using direct methods. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00216"},{"key":"ref_58","unstructured":"Paszke, A., Gross, S., Chintala, S., Chanan, G., Yang, E., DeVito, Z., Lin, Z., Desmaison, A., Antiga, L., and Lerer, A. (2017). Automatic differentiation in pytorch. Advances in Neural Information Processing Systems, The MIT Press."},{"key":"ref_59","unstructured":"Loshchilov, I., and Hutter, F. (2017). Decoupled weight decay regularization. arXiv."},{"key":"ref_60","unstructured":"Larsson, G., Maire, M., and Shakhnarovich, G. (2016). Fractalnet: Ultra-deep neural networks without residuals. arXiv."},{"key":"ref_61","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., and Fei-Fei, L. (2009, January 20\u201325). Imagenet: A large-scale hierarchical image database. Proceedings of the 2009 IEEE Conference on Computer Vision and Pattern Recognition, Miami, FL, USA.","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref_62","doi-asserted-by":"crossref","first-page":"2624","DOI":"10.1109\/TPAMI.2019.2930258","article-title":"Every pixel counts++: Joint learning of geometry and motion with 3d holistic understanding","volume":"42","author":"Luo","year":"2019","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."}],"container-title":["Computers"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2073-431X\/15\/1\/19\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,6]],"date-time":"2026-01-06T08:54:21Z","timestamp":1767689661000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2073-431X\/15\/1\/19"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,4]]},"references-count":62,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,1]]}},"alternative-id":["computers15010019"],"URL":"https:\/\/doi.org\/10.3390\/computers15010019","relation":{},"ISSN":["2073-431X"],"issn-type":[{"type":"electronic","value":"2073-431X"}],"subject":[],"published":{"date-parts":[[2026,1,4]]}}}