{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T21:16:15Z","timestamp":1783199775363,"version":"3.54.6"},"reference-count":67,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100016073","name":"Aviation Science Fund","doi-asserted-by":"publisher","award":["20230058048013"],"award-info":[{"award-number":["20230058048013"]}],"id":[{"id":"10.13039\/501100016073","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Engineering Applications of Artificial Intelligence"],"published-print":{"date-parts":[[2026,8]]},"DOI":"10.1016\/j.engappai.2026.114928","type":"journal-article","created":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T20:49:34Z","timestamp":1778273374000},"page":"114928","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"P1","title":["Image-plane geometric decoding for view-invariant indoor scene reconstruction"],"prefix":"10.1016","volume":"178","author":[{"given":"Mingyang","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yimeng","family":"Fan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Changsong","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lixue","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xin","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yanyan","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.engappai.2026.114928_b1","article-title":"Enhanced anomaly detection in pandemic surveillance videos: An attention approach with EfficientNet-B0 and CBAM integration","author":"Amin","year":"2024","journal-title":"IEEE Access"},{"key":"10.1016\/j.engappai.2026.114928_b2","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2023.120391","article-title":"Deep learning based active learning technique for data annotation and improve the overall performance of classification models","volume":"228","author":"Amin","year":"2023","journal-title":"Expert Syst. Appl."},{"key":"10.1016\/j.engappai.2026.114928_b3","doi-asserted-by":"crossref","DOI":"10.1016\/j.bspc.2023.105408","article-title":"An automated chest X-ray analysis for COVID-19, tuberculosis, and pneumonia employing ensemble learning approach","volume":"87","author":"Amin","year":"2024","journal-title":"Biomed. Signal Process. Control"},{"key":"10.1016\/j.engappai.2026.114928_b4","doi-asserted-by":"crossref","unstructured":"Barron, J.T., Mildenhall, B., Tancik, M., Hedman, P., Martin-Brualla, R., Srinivasan, P.P., 2021. Mip-nerf: A multiscale representation for anti-aliasing neural radiance fields. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 5855\u20135864.","DOI":"10.1109\/ICCV48922.2021.00580"},{"key":"10.1016\/j.engappai.2026.114928_b5","first-page":"1403","article-title":"Transformerfusion: Monocular rgb scene reconstruction using transformers","volume":"34","author":"Bozic","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.engappai.2026.114928_b6","doi-asserted-by":"crossref","unstructured":"Cao, A.-Q., de Charette, R., 2023. Scenerf: Self-supervised monocular 3d scene reconstruction with radiance fields. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 9387\u20139398.","DOI":"10.1109\/ICCV51070.2023.00861"},{"key":"10.1016\/j.engappai.2026.114928_b7","doi-asserted-by":"crossref","unstructured":"Chen, Z., Funkhouser, T., Hedman, P., Tagliasacchi, A., 2023. Mobilenerf: Exploiting the polygon rasterization pipeline for efficient neural field rendering on mobile architectures. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 16569\u201316578.","DOI":"10.1109\/CVPR52729.2023.01590"},{"key":"10.1016\/j.engappai.2026.114928_b8","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2025.111231","article-title":"High-resolution multi-view stereo with multi-scale feature fusion","volume":"157","author":"Chen","year":"2025","journal-title":"Eng. Appl. Artif. Intell."},{"key":"10.1016\/j.engappai.2026.114928_b9","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2023.106366","article-title":"Deep learning framework-based 3D shape reconstruction of tanks from a single RGB image","volume":"123","author":"Chen","year":"2023","journal-title":"Eng. Appl. Artif. Intell."},{"key":"10.1016\/j.engappai.2026.114928_b10","article-title":"DetailRecon: Focusing on detailed regions for online monocular 3D reconstruction","author":"Chu","year":"2025","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.engappai.2026.114928_b11","doi-asserted-by":"crossref","unstructured":"Dai, A., Chang, A.X., Savva, M., Halber, M., Funkhouser, T., Nie\u00dfner, M., 2017. Scannet: Richly-annotated 3d reconstructions of indoor scenes. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 5828\u20135839.","DOI":"10.1109\/CVPR.2017.261"},{"key":"10.1016\/j.engappai.2026.114928_b12","doi-asserted-by":"crossref","unstructured":"Duzceker, A., Galliani, S., Vogel, C., Speciale, P., Dusmanu, M., Pollefeys, M., 2021. Deepvideomvs: Multi-view stereo on video with recurrent spatio-temporal fusion. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 15324\u201315333.","DOI":"10.1109\/CVPR46437.2021.01507"},{"key":"10.1016\/j.engappai.2026.114928_b13","doi-asserted-by":"crossref","unstructured":"Feng, Z., Yang, L., Guo, P., Li, B., 2023. CVRecon: Rethinking 3d geometric feature learning for neural reconstruction. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 17750\u201317760.","DOI":"10.1109\/ICCV51070.2023.01627"},{"key":"10.1016\/j.engappai.2026.114928_b14","series-title":"Computer Vision: a Modern Approach","author":"Forsyth","year":"2002"},{"key":"10.1016\/j.engappai.2026.114928_b15","series-title":"3D reconstruction with generalizable neural fields using scene priors","author":"Fu","year":"2023"},{"issue":"1\u20132","key":"10.1016\/j.engappai.2026.114928_b16","first-page":"1","article-title":"Multi-view stereo: A tutorial","volume":"9","author":"Furukawa","year":"2015","journal-title":"Found. Trends\u00ae Comput. Graph. Vis."},{"key":"10.1016\/j.engappai.2026.114928_b17","doi-asserted-by":"crossref","unstructured":"Gao, H., Mao, W., Liu, M., 2023. VisFusion: Visibility-aware Online 3D Scene Reconstruction from Videos. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 17317\u201317326.","DOI":"10.1109\/CVPR52729.2023.01661"},{"key":"10.1016\/j.engappai.2026.114928_b18","series-title":"Efficiently modeling long sequences with structured state spaces","author":"Gu","year":"2021"},{"key":"10.1016\/j.engappai.2026.114928_b19","series-title":"2014 IEEE International Conference on Robotics and Automation","first-page":"1524","article-title":"A benchmark for RGB-D visual odometry, 3D reconstruction and SLAM","author":"Handa","year":"2014"},{"key":"10.1016\/j.engappai.2026.114928_b20","series-title":"Multiple View Geometry in Computer Vision","author":"Hartley","year":"2003"},{"key":"10.1016\/j.engappai.2026.114928_b21","article-title":"SP-SLAM: Neural real-time dense SLAM with scene priors","author":"Hong","year":"2025","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.engappai.2026.114928_b22","doi-asserted-by":"crossref","unstructured":"Hou, Y., Kannala, J., Solin, A., 2019. Multi-view stereo by temporal nonparametric fusion. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 2651\u20132660.","DOI":"10.1109\/ICCV.2019.00274"},{"key":"10.1016\/j.engappai.2026.114928_b23","series-title":"Dpsnet: End-to-end deep plane sweep stereo","author":"Im","year":"2019"},{"key":"10.1016\/j.engappai.2026.114928_b24","series-title":"Programming with TensorFlow: Solution for Edge Computing Applications","first-page":"87","article-title":"PyTorch","author":"Imambi","year":"2021"},{"key":"10.1016\/j.engappai.2026.114928_b25","doi-asserted-by":"crossref","unstructured":"Izadi, S., Kim, D., Hilliges, O., Molyneaux, D., Newcombe, R., Kohli, P., Shotton, J., Hodges, S., Freeman, D., Davison, A., et al., 2011. Kinectfusion: real-time 3d reconstruction and interaction using a moving depth camera. In: Proceedings of the 24th Annual ACM Symposium on User Interface Software and Technology. pp. 559\u2013568.","DOI":"10.1145\/2047196.2047270"},{"key":"10.1016\/j.engappai.2026.114928_b26","article-title":"Spatial transformer networks","volume":"28","author":"Jaderberg","year":"2015","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.engappai.2026.114928_b27","doi-asserted-by":"crossref","unstructured":"Ji, M., Gall, J., Zheng, H., Liu, Y., Fang, L., 2017. Surfacenet: An end-to-end 3d neural network for multiview stereopsis. In: Proceedings of the IEEE International Conference on Computer Vision. pp. 2307\u20132315.","DOI":"10.1109\/ICCV.2017.253"},{"key":"10.1016\/j.engappai.2026.114928_b28","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2023.107678","article-title":"Geometry perception and motion planning in robotic assembly based on semantic segmentation and point clouds reconstruction","volume":"130","author":"Jiang","year":"2024","journal-title":"Eng. Appl. Artif. Intell."},{"key":"10.1016\/j.engappai.2026.114928_b29","article-title":"Graph-based knowledge driven approach for violence detection","author":"Khan","year":"2024","journal-title":"IEEE Consum. Electron. Mag."},{"key":"10.1016\/j.engappai.2026.114928_b30","series-title":"Intelligent Multimedia Signal Processing for Smart Ecosystems","first-page":"307","article-title":"Advanced sequence learning approaches for emotion recognition using speech signals","author":"Khan","year":"2023"},{"key":"10.1016\/j.engappai.2026.114928_b31","doi-asserted-by":"crossref","unstructured":"Li, J., Feng, Z., She, Q., Ding, H., Wang, C., Lee, G.H., 2021. Mine: Towards continuous depth mpi with nerf for novel view synthesis. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 12578\u201312588.","DOI":"10.1109\/ICCV48922.2021.01235"},{"key":"10.1016\/j.engappai.2026.114928_b32","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2025.110550","article-title":"A hybrid architecture of sparse convolutional neural network-transformer for enhanced spatial-geometric feature learning in surface reconstruction","volume":"150","author":"Li","year":"2025","journal-title":"Eng. Appl. Artif. Intell."},{"issue":"12","key":"10.1016\/j.engappai.2026.114928_b33","doi-asserted-by":"crossref","first-page":"7630","DOI":"10.1109\/TCSVT.2023.3276753","article-title":"Hybrid-MVS: Robust multi-view reconstruction with hybrid optimization of visual and depth cues","volume":"33","author":"Li","year":"2023","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.engappai.2026.114928_b34","doi-asserted-by":"crossref","unstructured":"Liu, C., Gu, J., Kim, K., Narasimhan, S.G., Kautz, J., 2019. Neural rgb (r) d sensing: Depth and uncertainty from a video camera. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 10986\u201310995.","DOI":"10.1109\/CVPR.2019.01124"},{"key":"10.1016\/j.engappai.2026.114928_b35","doi-asserted-by":"crossref","unstructured":"Long, X., Liu, L., Li, W., Theobalt, C., Wang, W., 2021. Multi-view depth estimation using epipolar spatio-temporal networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 8258\u20138267.","DOI":"10.1109\/CVPR46437.2021.00816"},{"key":"10.1016\/j.engappai.2026.114928_b36","series-title":"Seminal Graphics: Pioneering Efforts that Shaped the Field","first-page":"347","article-title":"Marching cubes: A high resolution 3D surface construction algorithm","author":"Lorensen","year":"1998"},{"issue":"1","key":"10.1016\/j.engappai.2026.114928_b37","doi-asserted-by":"crossref","first-page":"99","DOI":"10.1145\/3503250","article-title":"Nerf: Representing scenes as neural radiance fields for view synthesis","volume":"65","author":"Mildenhall","year":"2021","journal-title":"Commun. ACM"},{"issue":"2","key":"10.1016\/j.engappai.2026.114928_b38","doi-asserted-by":"crossref","first-page":"438","DOI":"10.1137\/080732730","article-title":"ASIFT: A new framework for fully affine invariant image comparison","volume":"2","author":"Morel","year":"2009","journal-title":"SIAM J. Imaging Sci."},{"key":"10.1016\/j.engappai.2026.114928_b39","series-title":"Computer Vision\u2013ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part VII 16","first-page":"414","article-title":"Atlas: End-to-end 3d scene reconstruction from posed images","author":"Murez","year":"2020"},{"key":"10.1016\/j.engappai.2026.114928_b40","doi-asserted-by":"crossref","unstructured":"Othmani, A., Khan, M., El Saddik, A., Moreira, H.C., 2025. ARNet: Enhanced Tracking and Optimization for Video-Based Affect Recognition. In: Proceedings of the 2025 7th International Conference on Image, Video and Signal Processing. pp. 114\u2013120.","DOI":"10.1145\/3749859.3749874"},{"key":"10.1016\/j.engappai.2026.114928_b41","series-title":"Physically Based Rendering: From Theory to Implementation","author":"Pharr","year":"2023"},{"key":"10.1016\/j.engappai.2026.114928_b42","article-title":"Inner-outer aware reconstruction model for monocular 3D scene reconstruction","volume":"36","author":"Qiu","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.engappai.2026.114928_b43","series-title":"Vm-unet: Vision mamba unet for medical image segmentation","author":"Ruan","year":"2024"},{"key":"10.1016\/j.engappai.2026.114928_b44","series-title":"European Conference on Computer Vision","first-page":"1","article-title":"SimpleRecon: 3D reconstruction without 3D convolutions","author":"Sayed","year":"2022"},{"key":"10.1016\/j.engappai.2026.114928_b45","doi-asserted-by":"crossref","unstructured":"Schonberger, J.L., Frahm, J.-M., 2016. Structure-from-motion revisited. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 4104\u20134113.","DOI":"10.1109\/CVPR.2016.445"},{"key":"10.1016\/j.engappai.2026.114928_b46","series-title":"Computer Vision\u2013ECCV 2016: 14th European Conference, Amsterdam, the Netherlands, October 11-14, 2016, Proceedings, Part III 14","first-page":"501","article-title":"Pixelwise view selection for unstructured multi-view stereo","author":"Sch\u00f6nberger","year":"2016"},{"key":"10.1016\/j.engappai.2026.114928_b47","series-title":"GroupMamba: Parameter-efficient and accurate group visual state space model","author":"Shaker","year":"2024"},{"key":"10.1016\/j.engappai.2026.114928_b48","series-title":"FineRecon: Depth-aware feed-forward network for detailed 3D reconstruction","author":"Stier","year":"2023"},{"key":"10.1016\/j.engappai.2026.114928_b49","series-title":"2021 International Conference on 3D Vision","first-page":"320","article-title":"Vortx: Volumetric 3d reconstruction with transformers for voxelwise view selection and fusion","author":"Stier","year":"2021"},{"key":"10.1016\/j.engappai.2026.114928_b50","series-title":"2012 IEEE\/RSJ International Conference on Intelligent Robots and Systems","first-page":"573","article-title":"A benchmark for the evaluation of RGB-D SLAM systems","author":"Sturm","year":"2012"},{"key":"10.1016\/j.engappai.2026.114928_b51","doi-asserted-by":"crossref","unstructured":"Sun, J., Xie, Y., Chen, L., Zhou, X., Bao, H., 2021. NeuralRecon: Real-time coherent 3D reconstruction from monocular video. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 15598\u201315607.","DOI":"10.1109\/CVPR46437.2021.01534"},{"key":"10.1016\/j.engappai.2026.114928_b52","doi-asserted-by":"crossref","unstructured":"Tan, M., Chen, B., Pang, R., Vasudevan, V., Sandler, M., Howard, A., Le, Q.V., 2019. Mnasnet: Platform-aware neural architecture search for mobile. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 2820\u20132828.","DOI":"10.1109\/CVPR.2019.00293"},{"issue":"9","key":"10.1016\/j.engappai.2026.114928_b53","doi-asserted-by":"crossref","first-page":"1555","DOI":"10.3390\/math10091555","article-title":"EADN: An efficient deep learning model for anomaly detection in videos","volume":"10","author":"Ul Amin","year":"2022","journal-title":"Mathematics"},{"key":"10.1016\/j.engappai.2026.114928_b54","doi-asserted-by":"crossref","unstructured":"Wang, J., Chen, M., Karaev, N., Vedaldi, A., Rupprecht, C., Novotny, D., 2025. Vggt: Visual geometry grounded transformer. In: Proceedings of the Computer Vision and Pattern Recognition Conference. pp. 5294\u20135306.","DOI":"10.1109\/CVPR52734.2025.00499"},{"key":"10.1016\/j.engappai.2026.114928_b55","series-title":"Neus: Learning neural implicit surfaces by volume rendering for multi-view reconstruction","author":"Wang","year":"2021"},{"key":"10.1016\/j.engappai.2026.114928_b56","series-title":"2018 International Conference on 3D Vision","first-page":"248","article-title":"Mvdepthnet: Real-time multiview depth estimation neural network","author":"Wang","year":"2018"},{"key":"10.1016\/j.engappai.2026.114928_b57","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2025.113411","article-title":"A NeRF-based technique combined depth-guided filtering and view enhanced module for large-scale scene reconstruction","author":"Wen","year":"2025","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.engappai.2026.114928_b58","series-title":"2020 IEEE\/RSJ International Conference on Intelligent Robots and Systems","first-page":"10100","article-title":"Video depth estimation by fusing flow-to-depth proposals","author":"Xie","year":"2020"},{"key":"10.1016\/j.engappai.2026.114928_b59","doi-asserted-by":"crossref","unstructured":"Yang, L., Kang, B., Huang, Z., Xu, X., Feng, J., Zhao, H., 2024a. Depth anything: Unleashing the power of large-scale unlabeled data. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 10371\u201310381.","DOI":"10.1109\/CVPR52733.2024.00987"},{"key":"10.1016\/j.engappai.2026.114928_b60","doi-asserted-by":"crossref","first-page":"21875","DOI":"10.52202\/079017-0688","article-title":"Depth anything v2","volume":"37","author":"Yang","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.engappai.2026.114928_b61","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2023.107800","article-title":"SA-MVSNet: Self-attention-based multi-view stereo network for 3D reconstruction of images with weak texture","volume":"131","author":"Yang","year":"2024","journal-title":"Eng. Appl. Artif. Intell."},{"key":"10.1016\/j.engappai.2026.114928_b62","doi-asserted-by":"crossref","unstructured":"Yao, Y., Luo, Z., Li, S., Fang, T., Quan, L., 2018. Mvsnet: Depth inference for unstructured multi-view stereo. In: Proceedings of the European Conference on Computer Vision. ECCV, pp. 767\u2013783.","DOI":"10.1007\/978-3-030-01237-3_47"},{"issue":"1","key":"10.1016\/j.engappai.2026.114928_b63","doi-asserted-by":"crossref","first-page":"110","DOI":"10.1109\/TCSVT.2023.3285479","article-title":"EC-SfM: Efficient covisibility-based structure-from-motion for both sequential and unordered images","volume":"34","author":"Ye","year":"2024","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.engappai.2026.114928_b64","doi-asserted-by":"crossref","unstructured":"Yu, A., Ye, V., Tancik, M., Kanazawa, A., 2021. pixelnerf: Neural radiance fields from one or few images. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 4578\u20134587.","DOI":"10.1109\/CVPR46437.2021.00455"},{"key":"10.1016\/j.engappai.2026.114928_b65","series-title":"Monocular scene reconstruction with 3D SDF transformers","author":"Yuan","year":"2023"},{"key":"10.1016\/j.engappai.2026.114928_b66","doi-asserted-by":"crossref","unstructured":"Zheng, E., Dunn, E., Jojic, V., Frahm, J.-M., 2014. Patchmatch based joint view selection and depthmap estimation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 1510\u20131517.","DOI":"10.1109\/CVPR.2014.196"},{"key":"10.1016\/j.engappai.2026.114928_b67","series-title":"EPRecon: An efficient framework for real-time panoptic 3D reconstruction from monocular video","author":"Zhou","year":"2024"}],"container-title":["Engineering Applications of Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0952197626012108?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0952197626012108?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T20:32:25Z","timestamp":1783197145000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0952197626012108"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8]]},"references-count":67,"alternative-id":["S0952197626012108"],"URL":"https:\/\/doi.org\/10.1016\/j.engappai.2026.114928","relation":{},"ISSN":["0952-1976"],"issn-type":[{"value":"0952-1976","type":"print"}],"subject":[],"published":{"date-parts":[[2026,8]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Image-plane geometric decoding for view-invariant indoor scene reconstruction","name":"articletitle","label":"Article Title"},{"value":"Engineering Applications of Artificial Intelligence","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.engappai.2026.114928","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"114928"}}