{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T02:18:18Z","timestamp":1760235498876,"version":"build-2065373602"},"reference-count":30,"publisher":"MDPI AG","issue":"9","license":[{"start":{"date-parts":[[2021,8,30]],"date-time":"2021-08-30T00:00:00Z","timestamp":1630281600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100010661","name":"Horizon 2020 Framework Programme","doi-asserted-by":"publisher","award":["833704"],"award-info":[{"award-number":["833704"]}],"id":[{"id":"10.13039\/100010661","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J. Imaging"],"abstract":"<jats:p>Being able to robustly reconstruct 3D faces from 2D images is a topic of pivotal importance for a variety of computer vision branches, such as face analysis and face recognition, whose applications are steadily growing. Unlike 2D facial images, 3D facial data are less affected by lighting conditions and pose. Recent advances in the computer vision field have enabled the use of convolutional neural networks (CNNs) for the production of 3D facial reconstructions from 2D facial images. This paper proposes a novel CNN-based method which targets 3D facial reconstruction from two facial images, one in front and one from the side, as are often available to law enforcement agencies (LEAs). The proposed CNN was trained on both synthetic and real facial data. We show that the proposed network was able to predict 3D faces in the MICC Florence dataset with greater accuracy than the current state-of-the-art. Moreover, a scheme for using the proposed network in cases where only one facial image is available is also presented. This is achieved by introducing an additional network whose task is to generate a rotated version of the original image, which in conjunction with the original facial image, make up the image pair used for reconstruction via the previous method.<\/jats:p>","DOI":"10.3390\/jimaging7090169","type":"journal-article","created":{"date-parts":[[2021,8,30]],"date-time":"2021-08-30T11:01:37Z","timestamp":1630321297000},"page":"169","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Robust 3D Face Reconstruction Using One\/Two Facial Images"],"prefix":"10.3390","volume":"7","author":[{"given":"Ola","family":"Lium","sequence":"first","affiliation":[{"name":"System Development, Dfind Consulting, Akersgata 7, 0158 Oslo, Norway"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5621-3548","authenticated-orcid":false,"given":"Yong Bin","family":"Kwon","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Norwegian University of Science and Technology, Gl\u00f8shaugen, Sem S\u00e6lands vei 9, 7034 Trondheim, Norway"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5925-2179","authenticated-orcid":false,"given":"Antonios","family":"Danelakis","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Norwegian University of Science and Technology, Gl\u00f8shaugen, Sem S\u00e6lands vei 9, 7034 Trondheim, Norway"}]},{"given":"Theoharis","family":"Theoharis","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Norwegian University of Science and Technology, Gl\u00f8shaugen, Sem S\u00e6lands vei 9, 7034 Trondheim, Norway"}]}],"member":"1968","published-online":{"date-parts":[[2021,8,30]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Bagdanov, A.D., Del Bimbo, A., and Masi, I. (2011, January 1). The Florence 2D\/3D hybrid face dataset. Proceedings of the 2011 Joint ACM Workshop on Human Gesture and Behavior Understanding, Scottsdale, AZ, USA.","DOI":"10.1145\/2072572.2072597"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Lattas, A., Moschoglou, S., Gecer, B., Ploumpis, S., Triantafyllou, V., Ghosh, A., and Zafeiriou, S. (2020, January 13\u201319). AvatarMe: Realistically Renderable 3D Facial Reconstruction \u201cIn-the-Wild\u201d. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.","DOI":"10.1109\/CVPR42600.2020.00084"},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Wang, X., Guo, Y., Deng, B., and Zhang, J. (2020, January 13\u201319). Lightweight photometric stereo for facial details recovery. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.","DOI":"10.1109\/CVPR42600.2020.00082"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Feng, Y., Wu, F., Shao, X., Wang, Y., and Zhou, X. (2018, January 8\u201314). Joint 3D face reconstruction and dense alignment with position map regression network. Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany.","DOI":"10.1007\/978-3-030-01264-9_33"},{"key":"ref_5","unstructured":"Piao, J., Qian, C., and Li, H. (November, January 27). Semi-supervised monocular 3D face reconstruction with end-to-end shape-preserved domain transfer. Proceedings of the IEEE\/CVF International Conference on Computer Vision, Seoul, Korea."},{"key":"ref_6","unstructured":"Zeng, X., Peng, X., and Qiao, Y. (November, January 27). DF2Net: A dense-fine-finer network for detailed 3D face reconstruction. Proceedings of the IEEE\/CVF International Conference on Computer Vision, Seoul, Korea."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"180681","DOI":"10.1109\/ACCESS.2020.3028106","article-title":"3D Face Reconstruction From Single 2D Image Using Distinctive Features","volume":"8","author":"Afzal","year":"2020","journal-title":"IEEE Access"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Wu, F., Bao, L., Chen, Y., Ling, Y., Song, Y., Li, S., Ngan, K.N., and Liu, W. (2019, January 15\u201320). Mvf-net: Multi-view 3D face morphable model regression. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.00105"},{"key":"ref_9","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: From single image to image set. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops, Long Beach, CA, USA.","DOI":"10.1109\/CVPRW.2019.00038"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Blanz, V., and Vetter, T. (1999, January 8\u201313). A morphable model for the synthesis of 3D faces. Proceedings of the 26th Annual Conference on Computer Graphics and Interactive Techniques, Los Angeles, CA, USA.","DOI":"10.1145\/311535.311556"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Jourabloo, A., and Liu, X. (2016, January 27\u201330). Large-pose face alignment via CNN-based dense 3D model fitting. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.454"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Richardson, E., Sela, M., and Kimmel, R. (2016, January 25\u201328). 3D face reconstruction by learning from synthetic data. Proceedings of the 2016 Fourth International Conference on 3D Vision (3DV), Stanford, CA, USA.","DOI":"10.1109\/3DV.2016.56"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Tuan Tran, A., Hassner, T., Masi, I., and Medioni, G. (2017, January 21\u201326). Regressing robust and discriminative 3D morphable models with a very deep neural network. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.163"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Booth, J., Antonakos, E., Ploumpis, S., Trigeorgis, G., Panagakis, Y., and Zafeiriou, S. (2017, January 21\u201326). 3D face morphable models \u201cin-the-wild\u201d. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.580"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Genova, K., Cole, F., Maschinot, A., Sarna, A., Vlasic, D., and Freeman, W.T. (2018, January 18\u201323). Unsupervised training for 3D morphable model regression. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00874"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Jackson, A.S., Bulat, A., Argyriou, V., and Tzimiropoulos, G. (2017, January 22\u201329). Large pose 3D face reconstruction from a single image via direct volumetric CNN regression. Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy.","DOI":"10.1109\/ICCV.2017.117"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Gecer, B., Ploumpis, S., Kotsia, I., and Zafeiriou, S. (2019, January 15\u201320). GanFit: Generative adversarial network fitting for high fidelity 3d face reconstruction. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.00125"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Zhu, X., Lei, Z., Liu, X., Shi, H., and Li, S.Z. (2016, January 27\u201330). Face alignment across large poses: A 3D solution. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.23"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Guo, J., Zhu, X., Yang, Y., Yang, F., Lei, Z., and Li, S.Z. (2020). Towards fast, accurate and stable 3D dense face alignment. arXiv.","DOI":"10.1007\/978-3-030-58529-7_10"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Sandler, M., Howard, A.G., Zhu, M., Zhmoginov, A., and Chen, L. (2018). Inverted Residuals and Linear Bottlenecks: Mobile Networks for Classification, Detection and Segmentation. arXiv.","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (2015). Deep Residual Learning for Image Recognition. arXiv.","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Paysan, P., Knothe, R., Amberg, B., Romdhani, S., and Vetter, T. (2009, January 2\u20134). A 3D Face Model for Pose and Illumination Invariant Face Recognition. Proceedings of the 2009 Sixth IEEE International Conference on Advanced Video and Signal Based Surveillance, Genova, Italy.","DOI":"10.1109\/AVSS.2009.58"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1016\/j.imavis.2016.01.002","article-title":"300 Faces In-the-Wild Challenge: Database and results","volume":"47","author":"Sagonas","year":"2016","journal-title":"Image Vision Comput."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Barbosa, I.B., Cristani, M., Caputo, B., Rognhaugen, A., and Theoharis, T. (2017). Looking Beyond Appearances: Synthetic Training Data for Deep CNNs in Re-identification. arXiv.","DOI":"10.1016\/j.cviu.2017.12.002"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Kortylewski, A., Egger, B., Schneider, A., Gerig, T., Morel-Forster, A., and Vetter, T. (2019, January 16\u201320). Analyzing and Reducing the Damage of Dataset Bias to Face Recognition With Synthetic Data. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, Long Beach, CA, USA.","DOI":"10.1109\/CVPRW.2019.00279"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Theoharis, T., Papaioannou, G., Platis, N., and Patrikalakis, N.M. (2008). Graphics and Visualization: Principles & Algorithms, CRC Press.","DOI":"10.1201\/b10676"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Cimpoi, M., Maji, S., Kokkinos, I., Mohamed, S., and Vedaldi, A. (2014, January 23\u201328). Describing Textures in the Wild. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Columbus, OH, USA.","DOI":"10.1109\/CVPR.2014.461"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Zhou, H., Liu, J., Liu, Z., Liu, Y., and Wang, X. (2020, January 13\u201319). Rotate-and-render: Unsupervised photorealistic face rotation from single-view images. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.","DOI":"10.1109\/CVPR42600.2020.00595"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"807","DOI":"10.1016\/j.imavis.2009.08.002","article-title":"Multi-pie","volume":"28","author":"Gross","year":"2010","journal-title":"Image Vis. Comput."},{"key":"ref_30","first-page":"586","article-title":"Method for registration of 3-D shapes","volume":"Volume 1611","author":"Besl","year":"1992","journal-title":"Proceedings of the Sensor Fusion IV: Control Paradigms and Data Structures"}],"container-title":["Journal of Imaging"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2313-433X\/7\/9\/169\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T06:52:46Z","timestamp":1760165566000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2313-433X\/7\/9\/169"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,8,30]]},"references-count":30,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2021,9]]}},"alternative-id":["jimaging7090169"],"URL":"https:\/\/doi.org\/10.3390\/jimaging7090169","relation":{},"ISSN":["2313-433X"],"issn-type":[{"type":"electronic","value":"2313-433X"}],"subject":[],"published":{"date-parts":[[2021,8,30]]}}}