{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,10]],"date-time":"2026-05-10T05:23:26Z","timestamp":1778390606683,"version":"3.51.4"},"reference-count":49,"publisher":"MDPI AG","issue":"23","license":[{"start":{"date-parts":[[2023,11,22]],"date-time":"2023-11-22T00:00:00Z","timestamp":1700611200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Laboratory Innovation Foundation of the Chinese Academy of Science","award":["YJ22K002"],"award-info":[{"award-number":["YJ22K002"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Remote Sensing"],"abstract":"<jats:p>The reconstruction of 3D shapes from a single view has been a longstanding challenge. Previous methods have primarily focused on learning either geometric features that depict overall shape contours but are insufficient for occluded regions, local features that capture details but cannot represent the complete structure, or structural features that encode part relationships but require predefined semantics. However, the fusion of geometric, local, and structural features has been lacking, leading to inaccurate reconstruction of shapes with occlusions or novel compositions. To address this issue, we propose a two-stage approach for achieving 3D shape reconstruction. In the first stage, we encode the hierarchical structure features of the 3D shape using an encoder-decoder network. In the second stage, we enhance the hierarchical structure features by fusing them with global and point features and feed the enhanced features into a signed distance function (SDF) prediction network to obtain rough SDF values. Using the camera pose, we project arbitrary 3D points in space onto different depth feature maps of the CNN and obtain their corresponding positions. Then, we concatenate the features of these corresponding positions together to form local features. These local features are also fed into the SDF prediction network to obtain fine-grained SDF values. By fusing the two sets of SDF values, we improve the accuracy of the model and enable it to reconstruct other object types with higher quality. Comparative experiments demonstrate that the proposed method outperforms state-of-the-art approaches in terms of accuracy.<\/jats:p>","DOI":"10.3390\/rs15235449","type":"journal-article","created":{"date-parts":[[2023,11,22]],"date-time":"2023-11-22T03:54:37Z","timestamp":1700625277000},"page":"5449","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["ISHS-Net: Single-View 3D Reconstruction by Fusing Features of Image and Shape Hierarchical Structures"],"prefix":"10.3390","volume":"15","author":[{"given":"Guoqing","family":"Gao","sequence":"first","affiliation":[{"name":"Key Laboratory of Adaptive Optics, Chinese Academy of Sciences, Chengdu 610209, China"},{"name":"School of Optoelectronic Science and Engineering, University of Electronic Science and Technology of China, Chengdu 611731, China"},{"name":"Institute of Optics and Electronics Chinese Academy of Sciences, Chengdu 610209, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liang","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Computer Science, Southwest Petroleum University, Chengdu 610500, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7872-9518","authenticated-orcid":false,"given":"Quan","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science, Southwest Petroleum University, Chengdu 610500, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chongmin","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computer Science, Southwest Petroleum University, Chengdu 610500, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hua","family":"Bao","sequence":"additional","affiliation":[{"name":"Key Laboratory of Adaptive Optics, Chinese Academy of Sciences, Chengdu 610209, China"},{"name":"Institute of Optics and Electronics Chinese Academy of Sciences, Chengdu 610209, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Changhui","family":"Rao","sequence":"additional","affiliation":[{"name":"Key Laboratory of Adaptive Optics, Chinese Academy of Sciences, Chengdu 610209, China"},{"name":"School of Optoelectronic Science and Engineering, University of Electronic Science and Technology of China, Chengdu 611731, China"},{"name":"Institute of Optics and Electronics Chinese Academy of Sciences, Chengdu 610209, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2023,11,22]]},"reference":[{"key":"ref_1","unstructured":"Christopher, C., Xu, D., Gwak, J., Chen, K., and Savarese, S. (2016, January 11\u201314). 3d-r2n2: A unified approach for single and multi-view 3d object reconstruction. Proceedings of the European Conference on Computer Vision (ECCV), Amsterdam, The Netherlands."},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Tulsiani, S., Su, H., Guibas, L., Efros, A., and Malik, J. (2017, January 21\u201326). Learning Shape Abstractions by Assembling Volumetric Primitives. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.160"},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Charles, R., Su, H., Kaichun, M., and Guibas, L. (2017, January 21\u201326). PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.16"},{"key":"ref_4","first-page":"1","article-title":"MeshCNN: A network with an edge","volume":"38","author":"Hanocka","year":"2019","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Park, J., Florence, P., Straub, J., Newcombe, R., and Lovegrove, S. (2019, January 15\u201320). Deepsdf: Learning continuous signed distance functions for shape representation. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.00025"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3355089.3356527","article-title":"StructureNet: Hierarchical graph networks for 3D shape generation","volume":"38","author":"Mo","year":"2019","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"104368","DOI":"10.1016\/j.imavis.2021.104368","article-title":"A deep-shallow and global\u2013local multi-feature fusion network for photometric stereo","volume":"118","author":"Liu","year":"2022","journal-title":"Image Vis. Comput."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Mescheder, L., Oechsle, M., Niemeyer, M., Nowozin, S., and Geiger, A. (2019, January 15\u201320). Occupancy Networks: Learning 3D Reconstruction in Function Space. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.00459"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Yu, F., Liu, K., Zhang, Y., Zhu, C., and Xu, K. (2019, January 15\u201320). PartNet: A Recursive Part Decomposition Network for Fine-Grained and Hierarchical Shape Segmentation. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.00972"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Tang, J., Han, X., Pan, J., Jia, K., and Tong, X. (2019, January 15\u201320). A Skeleton-Bridged Deep Learning Approach for Generating Meshes of Complex Topologies From Single RGB Images. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.00467"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"1785","DOI":"10.1109\/TVCG.2021.3131712","article-title":"STD-Net: Structure-Preserving and Topology-Adaptive Deformation Network for Single-View 3D Reconstruction","volume":"29","author":"Mao","year":"2021","journal-title":"IEEE Trans. Vis. Comput. Graph."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Ju, Y., Jian, M., Dong, J., and Lam, K.-M. (2020, January 1\u20134). Learning photometric stereo via manifold-based mapping. 2020 IEEE International Conference on Visual Communications and Image Processing (VCIP), Macau, China.","DOI":"10.1109\/VCIP49819.2020.9301860"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"163","DOI":"10.1145\/37402.37422","article-title":"Marching cubes: A high-resolution 3D surface construction algorithm","volume":"21","author":"Lorensen","year":"1987","journal-title":"ACM SIGGRAPH Comput. Graph."},{"key":"ref_14","unstructured":"Qi, C., Yi, L., Su, H., and Guibas, L. (2017, January 4\u20139). Pointnet++: Deep hierarchical feature learning on point sets in a metric space. Proceedings of the Neural Information Processing Systems (NeurIPS), Long Beach, CA, USA."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Yang, Y., Feng, C., Shen, Y., and Tian, D. (2018, January 18\u201323). FoldingNet: Point Cloud Auto-Encoder via Deep Grid Deformation. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00029"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Dai, P., Zhang, Y., Li, Z., Liu, S., and Zeng, B. (2020, January 13\u201319). Neural Point Cloud Rendering via Multi-Plane Projection. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA.","DOI":"10.1109\/CVPR42600.2020.00785"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"3746","DOI":"10.1109\/TIP.2023.3279661","article-title":"Single-View 3D Mesh Reconstruction for Seen and Unseen Categories","volume":"32","author":"Yang","year":"2023","journal-title":"IEEE Trans. Image Process."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Hu, J., Wang, X., Liao, Z., and Xiao, T. (2023, January 10\u201314). M-GCN: Multi-scale Graph Convolutional Network for 3D Point Cloud Classification. Proceedings of the 2023 IEEE International Conference on Multimedia and Expo (ICME), Brisbane, Australia.","DOI":"10.1109\/ICME55011.2023.00163"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Wang, N., Zhang, Y., Li, Z., Fu, Y., Liu, W., and Jiang, Y. (2018, January 8\u201314). Pixel2mesh: Generating 3D mesh models from single RGB images. Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany.","DOI":"10.1007\/978-3-030-01252-6_4"},{"key":"ref_20","unstructured":"Alldieck, T., Pons-Moll, G., Theobalt, C., and Magnor, M. (November, January 27). Tex2Shape: Detailed Full Human Body Geometry From a Single Image. Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), Seoul, Republic of Korea."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Groueix, T., Fisher, M., Kim, V., Russell, B., and Aubry, M. (2018, January 18\u201323). AtlasNet: A Papier-M\u00e2ch\u00e9 Approach to Learning 3D Surface Generation. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00030"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Deng, Y., Yang, J., Xu, S., Chen, D., Jia, Y., and Tong, X. (2019, January 16\u201317). Accurate 3D Face Reconstruction With Weakly-Supervised Learning. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Long Beach, CA, USA.","DOI":"10.1109\/CVPRW.2019.00038"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Kato, H., Ushiku, Y., and Harada, T. (2018, January 18\u201323). Neural 3D Mesh Renderer. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00411"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Goel, S., Gkioxari, G., and Malik, J. (2022, January 18\u201324). Differentiable stereopsis: Meshes from multiple views using differentiable rendering. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, LA, USA.","DOI":"10.1109\/CVPR52688.2022.00844"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Worchel, M., Diaz, R., Hu, W., Schreer, O., Feldmann, I., and Eisert, P. (2022, January 18\u201324). Multi-view mesh reconstruction with neural deferred shading. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, LA, USA.","DOI":"10.1109\/CVPR52688.2022.00609"},{"key":"ref_26","first-page":"21638","article-title":"Neural unsigned distance fields for implicit function learning","volume":"33","author":"Chibane","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Aumentado-Armstrong, T., Tsogkas, S., Dickinson, S., and Jepson, A. (2022, January 18\u201324). Representing 3D shapes with probabilistic directed distance fields. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, LA, USA.","DOI":"10.1109\/CVPR52688.2022.01874"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Peleg, T., Szekely, P., Sabo, D., and Sendik, O. (2019, January 16\u201317). IM-Net for High Resolution Video Frame Interpolation. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.00250"},{"key":"ref_29","unstructured":"Wang, W., Xu, Q., Ceylan, D., Mech, R., and Neumann, U. (2019, January 8\u201314). DISN: Deep implicit surface network for high-quality single-view 3D reconstruction. Proceedings of the 33rd International Conference on Neural Information Processing Systems, Vancouver, BC, Canada."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Chibane, J., Alldieck, T., and Pons-Moll, G. (2020, January 13\u201319). Implicit Functions in Feature Space for 3D Shape Reconstruction and Completion. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA.","DOI":"10.1109\/CVPR42600.2020.00700"},{"key":"ref_31","unstructured":"Saito, S., Huang, Z., Natsume, R., Morishima, S., Li, H., and Kanazawa, A. (November, January 27). PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitization. Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), Seoul, Republic of Korea."},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Jiang, C., Sud, A., Makadia, A., Huang, J., Nie\u00dfner, M., and Funkhouser, T. (2020, January 13\u201319). Local Implicit Grid Representations for 3D Scenes. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA.","DOI":"10.1109\/CVPR42600.2020.00604"},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Midenhall, B., Srinvasan, P., Tancik, M., Barron, J., Ramamoorthi, R., and Ng, R. (2020, January 23\u201328). NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis. Proceedings of the European Conference on Computer Vision (ECCV), Glasgow, UK.","DOI":"10.1007\/978-3-030-58452-8_24"},{"key":"ref_34","first-page":"4805","article-title":"Volume rendering of neural implicit surfaces","volume":"34","author":"Yariv","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_35","first-page":"27171","article-title":"Neus: Learning neural implicit surfaces by volume rendering for multi-view reconstruction","volume":"34","author":"Wang","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Wu, R.D., Zhuang, Y.X., Xu, K., Zhang, H., and Chen, B.Q. (2020, January 13\u201319). PQ-NET: A generative part Seq2Seq network for 3D shapes. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA.","DOI":"10.1109\/CVPR42600.2020.00091"},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3526212","article-title":"DSG-net: Learning disentangled structure and geometry for 3D shape generation","volume":"42","author":"Yang","year":"2022","journal-title":"ACM Trans. Graph."},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Zou, C., Yumer, E., Yang, J., Ceylan, D., and Hoiem, D. (2017, January 22\u201329). 3D-PRNN: Generating Shape Primitives with Recurrent Neural Networks. Proceedings of the IEEE International Conference on Computer Vision (ICCV), Venice, Italy.","DOI":"10.1109\/ICCV.2017.103"},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3355089.3356488","article-title":"SDM-NET: Deep Generative Network for Structured Deformable Mesh","volume":"38","author":"Gao","year":"2019","journal-title":"ACM Trans. Graph."},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Yin, K., Chen, Z., Chaudhuri, S., Fisher, M., Kim, V., and Zhang, H. (2020, January 25\u201328). COALESCE: Component Assembly by Learning to Synthesize Connections. Proceedings of the International Conference on 3D Vision (3DV), Fukuoka, Japan.","DOI":"10.1109\/3DV50981.2020.00016"},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3414685.3417812","article-title":"ShapeAssembly: Learning to generate programs for 3D shape structure synthesis","volume":"39","author":"Jones","year":"2020","journal-title":"ACM Trans. Graph."},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Hui, K., Li, R., Hu, J., and Fu, C. (2022, January 18\u201324). Neural Template: Topology-aware Reconstruction and Disentangled Generation of 3D Meshes. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, LA, USA.","DOI":"10.1109\/CVPR52688.2022.01802"},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Ju, Y., Lam, K.M., Xiao, J., Zhang, C., Yang, C., and Dong, J. (2023, January 4\u201310). Efficient Feature Fusion for Learning-Based Photometric Stereo. Proceedings of the ICASSP 2023\u20132023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Rhodes, Greek.","DOI":"10.1109\/ICASSP49357.2023.10095806"},{"key":"ref_44","unstructured":"Chang, A., Funkhouser, T., Guibas, L., Hanrahan, P., Huang, Q., Li, Z., Savarese, S., Savva, M., Song, S., and Su, H. (2015). ShapeNet: An Information-Rich 3D Model Repository. arXiv."},{"key":"ref_45","doi-asserted-by":"crossref","unstructured":"Chen, Z., and Zhang, H. (2019, January 15\u201320). Learning implicit fields for generative shape modeling. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.00609"},{"key":"ref_46","doi-asserted-by":"crossref","unstructured":"Wang, W., Ceylan, D., Mech, R., and Neumann, U. (2019, January 15\u201320). 3DN: 3D Deformation Network. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.00113"},{"key":"ref_47","doi-asserted-by":"crossref","unstructured":"Li, M., and Zhang, H. (2021, January 19\u201325). D2im-net: Learning detail disentangled implicit fields from single images. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Nashville, TN, USA.","DOI":"10.1109\/CVPR46437.2021.01011"},{"key":"ref_48","doi-asserted-by":"crossref","unstructured":"Xu, Y., Fan, T., and Yuan, Y. (2020, January 23\u201328). Ladybird: Quasi-monte carlo sampling for deep implicit field based 3d reconstruction with symmetry. Proceedings of the European Conference on Computer Vision (ECCV), Glasgow, UK.","DOI":"10.1007\/978-3-030-58452-8_15"},{"key":"ref_49","doi-asserted-by":"crossref","unstructured":"Chen, W., Lin, C., Li, W., and Yang, B. (2022, January 18\u201324). 3PSDF: Three-Pole Signed Distance Function for Learning Surfaces with Arbitrary Topologies. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, LA, USA.","DOI":"10.1109\/CVPR52688.2022.01797"}],"container-title":["Remote Sensing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2072-4292\/15\/23\/5449\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T21:27:03Z","timestamp":1760131623000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2072-4292\/15\/23\/5449"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,22]]},"references-count":49,"journal-issue":{"issue":"23","published-online":{"date-parts":[[2023,12]]}},"alternative-id":["rs15235449"],"URL":"https:\/\/doi.org\/10.3390\/rs15235449","relation":{},"ISSN":["2072-4292"],"issn-type":[{"value":"2072-4292","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,11,22]]}}}