{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,14]],"date-time":"2026-10-14T10:29:33Z","timestamp":1791973773272,"version":"4.4.0"},"reference-count":59,"publisher":"MDPI AG","issue":"22","license":[{"start":{"date-parts":[[2025,11,12]],"date-time":"2025-11-12T00:00:00Z","timestamp":1762905600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Regional Innovation System & Education"},{"name":"Institute for Regional Innovation System & Education"},{"name":"Ministry of Education","award":["2025-RISE-02-001-018"],"award-info":[{"award-number":["2025-RISE-02-001-018"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>High-quality 3D objects play a crucial role in digital twins, while synthetic data generated from these objects have become essential in deep learning-based computer vision applications. The task of collecting and labeling real defects on industrial object surfaces has many challenges and efforts, while synthetic data generation feasibly replicates huge amounts of labeled data. However, synthetic datasets lack realism in their rendered images. To overcome this issue, this paper introduces a single framework for 3D industrial object reconstruction and synthetic defect generation for digital twin smart factory applications. In detail, NeRF is applied to reconstruct our custom industrial 3D objects through videos collected by a smartphone camera. Several NeRF-based models (i.e., Instant-NGP, Nerfacto, Volinga, and Tensorf) are compared to choose the best outcome for the next step of defect generation on the 3D object surface. To be fairly evaluated, we train four models using the Nerfstudio framework with our three custom datasets of two objects. From the experiment\u2019s results, Instant-NGP and Nerfacto achieve the best outcomes, outperforming all other methods significantly. The exported meshes of 3D objects are refined using Blender before loading into NVIDIA Omniverse Code to generate defects on the surface with the Replicator. To evaluate the object detection performance and to verify the benefits of synthetic defect data, we conducted experiments with YOLO-based models on our synthetic and real-plus-synthetic defects. From the experiment\u2019s results, the synthetic defect data contribute to improving YOLO models\u2019 generalization capability with the highest and lowest accuracy mAP@0.5 enhancement of 18.8 and 1.5 percent on YOLOv6n and YOLOv8s, respectively.<\/jats:p>","DOI":"10.3390\/s25226908","type":"journal-article","created":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T11:49:43Z","timestamp":1763120983000},"page":"6908","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Efficient Synthetic Defect on 3D Object Reconstruction and Generation Pipeline for Digital Twins Smart Factory"],"prefix":"10.3390","volume":"25","author":[{"given":"Viet-Hoan","family":"Nguyen","sequence":"first","affiliation":[{"name":"R&D Center, Intown Co., Ltd., Busan 08592, Republic of Korea"},{"name":"Department of Artificial Intelligence Convergence, Pukyong National University, Busan 48513, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Thi-Ngot","family":"Pham","sequence":"additional","affiliation":[{"name":"Department of Data Informatics, Korea Maritime & Ocean University, 727, Taejong-ro, Yeongdo-gu, Busan 49112, Republic of Korea"},{"name":"Interdisciplinary Major of Ocean Renewable Energy Engineering, Korea Maritime & Ocean University, 727, Taejong-ro, Yeongdo-gu, Busan 49112, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6735-6456","authenticated-orcid":false,"given":"Jun-Ho","family":"Huh","sequence":"additional","affiliation":[{"name":"Department of Data Informatics, Korea Maritime & Ocean University, 727, Taejong-ro, Yeongdo-gu, Busan 49112, Republic of Korea"},{"name":"Interdisciplinary Major of Ocean Renewable Energy Engineering, Korea Maritime & Ocean University, 727, Taejong-ro, Yeongdo-gu, Busan 49112, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3354-8975","authenticated-orcid":false,"given":"Pil-Joo","family":"Choi","sequence":"additional","affiliation":[{"name":"Department of Artificial Intelligence Convergence, Pukyong National University, Busan 48513, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4712-867X","authenticated-orcid":false,"given":"Young-Bong","family":"Kim","sequence":"additional","affiliation":[{"name":"Department of Artificial Intelligence Convergence, Pukyong National University, Busan 48513, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Oh-Heum","family":"Kwon","sequence":"additional","affiliation":[{"name":"Department of Artificial Intelligence Convergence, Pukyong National University, Busan 48513, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ki-Ryong","family":"Kwon","sequence":"additional","affiliation":[{"name":"Department of Artificial Intelligence Convergence, Pukyong National University, Busan 48513, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2025,11,12]]},"reference":[{"key":"ref_1","unstructured":"NVIDIA (2025, September 10). Transforming Industrial Defect Detection with NVIDIA TAO and Vision AI Models. Available online: https:\/\/developer.nvidia.com\/blog\/transforming-industrial-defect-detection-with-nvidia-tao-and-vision-ai-models\/."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"103907","DOI":"10.1016\/j.cviu.2023.103907","article-title":"Indoor synthetic data generation: A systematic review","volume":"240","author":"Schieber","year":"2024","journal-title":"Comput. Vis. Image Underst."},{"key":"ref_3","unstructured":"Unity Technologies (2025, September 10). Unity Documentation. Available online: https:\/\/docs.unity.com\/."},{"key":"ref_4","unstructured":"Epic Games (2025, September 10). Unreal Engine. Available online: https:\/\/www.unrealengine.com\/en-US."},{"key":"ref_5","unstructured":"NVIDIA (2025, September 10). Omniverse Replicator Extension. Available online: https:\/\/docs.omniverse.nvidia.com\/extensions\/latest\/ext_replicator.html."},{"key":"ref_6","unstructured":"Blender Foundation (2025, September 10). Blender. Available online: https:\/\/www.blender.org\/."},{"key":"ref_7","unstructured":"Aerial Precision (2025, September 10). Exploring the Precision of LiDAR Mapping: Unveiling Its Accuracy. Available online: https:\/\/www.aerial-precision.com\/blogs\/blog\/unveiling-the-precision-of-lidar-mapping-how-accurate-is-it-really."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"197","DOI":"10.1111\/j.1477-9730.1986.tb00557.x","article-title":"Industrial photogrammetry: New developments and recent applications","volume":"12","author":"Fraser","year":"2006","journal-title":"Photogramm. Rec."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"568","DOI":"10.3390\/s90100568","article-title":"State-of-the-art and applications of 3D imaging sensors in industry, cultural heritage, medicine, and criminal investigation","volume":"9","author":"Sansoni","year":"2009","journal-title":"Sensors"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"54","DOI":"10.1016\/j.optlastec.2015.04.011","article-title":"Procedure for quality inspection of welds based on macro-photogrammetric three-dimensional reconstruction","volume":"73","year":"2015","journal-title":"Opt. Laser Technol."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"1104","DOI":"10.3390\/rs3061104","article-title":"Heritage recording and 3D modeling with photogrammetry and 3D scanning","volume":"3","author":"Remondino","year":"2011","journal-title":"Remote Sens."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"675","DOI":"10.5194\/isprs-archives-XLI-B5-675-2016","article-title":"3D digitization of an heritage masterpiece\u2014A critical analysis on quality assessment","volume":"41","author":"Menna","year":"2016","journal-title":"Int. Arch. Photogramm. Remote Sens. Spat. Inf. Sci."},{"key":"ref_13","unstructured":"Stylianidis, E., and Remondino, F. (2016). 3D Recording, Documentation and Management of Cultural Heritage, Whittles Publishing."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"513","DOI":"10.5194\/isprs-archives-XLVI-2-W1-2022-513-2022","article-title":"Project Indigo\u2014Document, disseminate & analyse a graffiti-scape","volume":"46","author":"Verhoeven","year":"2022","journal-title":"Int. Arch. Photogramm. Remote Sens. Spat. Inf. Sci."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"269","DOI":"10.1111\/j.1477-9730.2006.00383.x","article-title":"Image-based 3D modelling: A review","volume":"21","author":"Remondino","year":"2006","journal-title":"Photogramm. Rec."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Wu, B., Zhou, Y., Qian, Y., Gong, M., and Huang, H. (2018). Full 3D reconstruction of transparent objects. arXiv.","DOI":"10.1145\/3197517.3201286"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"106883","DOI":"10.1016\/j.measurement.2019.106883","article-title":"Evaluation of synthetically generated patterns for image-based 3D reconstruction of texture-less objects","volume":"147","author":"Budak","year":"2019","journal-title":"Measurement"},{"key":"ref_18","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, \u0141., and Polosukhin, I. (2017, January 4\u20139). All you need is attention. Proceedings of the 31st Conference on Neural Information Processing Systems (NIPS 2017), Long Beach, CA, USA."},{"key":"ref_19","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"},{"key":"ref_20","unstructured":"Nerfstudio Project (2025, September 10). Nerfstudio: A Modular Framework for Neural Radiance Field Development. Available online: https:\/\/github.com\/nerfstudio-project\/nerfstudio\/."},{"key":"ref_21","unstructured":"NVLabs (2025, September 10). Instant Neural Graphics Primitives. Available online: https:\/\/github.com\/NVlabs\/instant-ngp."},{"key":"ref_22","first-page":"102","article-title":"Instant neural graphics primitives with a multiresolution hash encoding","volume":"41","author":"Evans","year":"2022","journal-title":"ACM Trans. Graph."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Tancik, M., Weber, E., Ng, E., Li, R., Yi, B., Wang, T., Kristoffersen, A., Austin, J., Salahi, K., and Ahuja, A. (2023). Nerfstudio: A modular framework for neural radiance field development. arXiv.","DOI":"10.1145\/3588432.3591516"},{"key":"ref_24","unstructured":"Volinga (2025, September 10). Volinga Model. Available online: https:\/\/github.com\/Volinga\/volinga-model."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Chen, A., Xu, Z., Geiger, A., Yu, J., and Su, H. (2022, January 23\u201327). TensoRF: Tensorial radiance fields. Proceedings of the 17th European Conference on Computer Vision, Tel Aviv, Israel.","DOI":"10.1007\/978-3-031-19824-3_20"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Wang, H., Sridhar, S., Huang, J., Valentin, J., Song, S., and Guibas, L.J. (2019, January 15\u201320). Normalized object coordinate space for category-level 6D object pose and size estimation. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.00275"},{"key":"ref_27","unstructured":"Chang, A.X., 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_28","doi-asserted-by":"crossref","unstructured":"Shi, G., Zhu, Y., Tremblay, J., Birchfield, S., Ramos, F., Anandkumar, A., and Zhu, Y. (June, January 30). Fast uncertainty quantification for deep object pose estimation. Proceedings of the 2021 IEEE International Conference on Robotics and Automation (ICRA), Xi\u2019an, China.","DOI":"10.1109\/ICRA48506.2021.9561483"},{"key":"ref_29","unstructured":"To, T., Tremblay, J., McKay, D., Yamaguchi, Y., Leung, K., Balanon, A., Cheng, J., Hodge, W., and Birchfield, S. (2018, January 22). NDDS: NVIDIA deep learning dataset synthesizer. Proceedings of the CVPR 2018 Workshop on Real World Challenges and New Benchmarks for Deep Learning in Robotic Vision, Salt Lake City, UT, USA."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Back, S., Lee, J., Kim, T., Noh, S., Kang, R., Bak, S., and Lee, K. (2022, January 23\u201327). Unseen object amodal instance segmentation via hierarchical occlusion modeling. Proceedings of the 2022 International Conference on Robotics and Automation (ICRA), Philadelphia, PA, USA.","DOI":"10.1109\/ICRA46639.2022.9811646"},{"key":"ref_31","unstructured":"Denninger, M., Sundermeyer, M., Winkelbauer, D., Olefir, D., Hodan, T., Zidan, Y., Elbadrawy, M., Knauer, M., Katam, H., and Lodhi, A. (2020, January 12\u201316). BlenderProc: Reducing the reality gap with photorealistic rendering. Proceedings of the Robotics: Science and Systems (RSS) Workshops, Corvalis, OR, USA."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"927","DOI":"10.1177\/0278364912445831","article-title":"The KIT object models database: An object model database for object recognition, localization and manipulation in service robotics","volume":"31","author":"Kasper","year":"2012","journal-title":"Int. J. Robot. Res."},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Singh, A., Sha, J., Narayan, K.S., Achim, T., and Abbeel, P. (June, January 31). BigBIRD: A large-scale 3D database of object instances. Proceedings of the 2014 IEEE International Conference on Robotics and Automation (ICRA), Hong Kong, China.","DOI":"10.1109\/ICRA.2014.6906903"},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Hoda\u0148, T., Sundermeyer, M., Drost, B., Labb\u00e9, Y., Brachmann, E., Michel, F., Rother, C., and Matas, J. (2020, January 23\u201328). BOP challenge 2020 on 6D object localization. Proceedings of the European Conference on Computer Vision Workshops, Glasgow, UK.","DOI":"10.1007\/978-3-030-66096-3_39"},{"key":"ref_35","unstructured":"Ng, Z., Wang, H., Zhang, Z., Hock, F.T.E., and Ang, M.H. (2023). SynTable: A synthetic data generation pipeline for unseen object amodal instance segmentation of cluttered tabletop scenes. arXiv."},{"key":"ref_36","unstructured":"NVIDIA (2025, September 10). Omniverse Isaac Sim Replicator Tutorial. Available online: https:\/\/docs.omniverse.nvidia.com\/extensions\/latest\/ext_replicator\/getting_started.html."},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Downs, L., Francis, A., Koenig, N., Kinman, B., Hickman, R., Reymann, K., McHugh, T.B., and Vanhoucke, V. (2022, January 23\u201327). Google scanned objects: A high-quality dataset of 3D scanned household items. Proceedings of the 2022 International Conference on Robotics and Automation (ICRA), Philadelphia, PA, USA.","DOI":"10.1109\/ICRA46639.2022.9811809"},{"key":"ref_38","unstructured":"NVIDIA (2025, September 10). NVIDIA Kit Extension Sample\u2014Defects Generation. Available online: https:\/\/github.com\/NVIDIA-Omniverse\/kit-extension-sample-defectsgen."},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Zeng, Y., Lei, J., Feng, T., Qin, X., Li, B., Wang, Y., Wang, D., and Song, J. (2023). Neural radiance fields-based 3D reconstruction of power transmission lines using progressive motion sequence images. Sensors, 23.","DOI":"10.3390\/s23239537"},{"key":"ref_40","first-page":"1051","article-title":"NeRF for heritage 3D reconstruction","volume":"48","author":"Mazzacca","year":"2022","journal-title":"Int. Arch. Photogramm. Remote Sens. Spat. Inf. Sci."},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Remondino, F., Karami, A., Yan, Z., Mazzacca, G., Rigon, S., and Qin, R. (2023). A critical analysis of NeRF-based 3D reconstruction. Remote Sens., 15.","DOI":"10.3390\/rs15143585"},{"key":"ref_42","unstructured":"Caruso, B., Mahendrakar, T., Nguyen, V.M., White, R.T., and Steffen, T. (2023). 3D reconstruction of non-cooperative resident space objects using instant NGP-accelerated NeRF and D-NeRF. arXiv."},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"71","DOI":"10.1049\/smt2.12131","article-title":"Research on 3D reconstruction technology of large-scale substation equipment based on NeRF","volume":"17","author":"Pei","year":"2023","journal-title":"IET Sci. Meas. Technol."},{"key":"ref_44","unstructured":"(2025, September 10). COLMAP. Available online: https:\/\/github.com\/colmap\/colmap."},{"key":"ref_45","unstructured":"Gao, K., Gao, Y., He, H., Lu, D., Xu, L., and Li, J. (2022). NeRF: Neural radiance field in 3D vision, a comprehensive review. arXiv."},{"key":"ref_46","unstructured":"(2025, September 10). Meshroom 3D Reconstruction Software. Available online: https:\/\/github.com\/alicevision\/Meshroom."},{"key":"ref_47","unstructured":"(2025, September 10). NeRF: Neural Radiance Fields. Available online: https:\/\/github.com\/bmild\/nerf."},{"key":"ref_48","unstructured":"SP Auto (2025, September 10). SP Auto Product Page. Available online: http:\/\/m.spauto.co.kr\/en\/m\/sub\/product\/auto.asp."},{"key":"ref_49","unstructured":"Ultralytics (2025, September 10). YOLOv5. Available online: https:\/\/github.com\/ultralytics\/yolov5\/releases\/tag\/v6.0."},{"key":"ref_50","unstructured":"Meituan (2025, September 10). YOLOv6. Available online: https:\/\/github.com\/meituan\/YOLOv6."},{"key":"ref_51","unstructured":"Megvii (2025, September 10). YOLOX. Available online: https:\/\/github.com\/Megvii-BaseDetection\/YOLOX."},{"key":"ref_52","unstructured":"Wong, K.Y. (2025, September 10). YOLOv7. Available online: https:\/\/github.com\/WongKinYiu\/yolov7."},{"key":"ref_53","unstructured":"Ultralytics (2025, September 10). YOLOv8. Available online: https:\/\/github.com\/ultralytics\/ultralytics."},{"key":"ref_54","unstructured":"THU-MIG (2025, September 10). YOLOv10. Available online: https:\/\/github.com\/THU-MIG\/yolov10."},{"key":"ref_55","unstructured":"Wong, K.Y. (2025, September 10). YOLOv9. Available online: https:\/\/github.com\/WongKinYiu\/yolov9."},{"key":"ref_56","unstructured":"(2025, October 21). NEU-DET. IEEE Dataport. Available online: https:\/\/ieee-dataport.org\/documents\/neu-det."},{"key":"ref_57","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_58","doi-asserted-by":"crossref","unstructured":"Zhang, R., Isola, P., Efros, A.A., Shechtman, E., and Wang, O. (2018, January 18\u201323). The unreasonable effectiveness of deep features as a perceptual metric. Proceedings of the 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref_59","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Doll\u00e1r, P., and Zitnick, C.L. (2014, January 6\u201312). Microsoft COCO: Common objects in context. Proceedings of the 13th European Conference on Computer Vision\u2014ECCV 2014, Zurich, Switzerland.","DOI":"10.1007\/978-3-319-10602-1_48"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/25\/22\/6908\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T05:12:26Z","timestamp":1763183546000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/25\/22\/6908"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,12]]},"references-count":59,"journal-issue":{"issue":"22","published-online":{"date-parts":[[2025,11]]}},"alternative-id":["s25226908"],"URL":"https:\/\/doi.org\/10.3390\/s25226908","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,12]]}}}