{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T00:02:48Z","timestamp":1768435368253,"version":"3.49.0"},"reference-count":55,"publisher":"MDPI AG","issue":"9","license":[{"start":{"date-parts":[[2020,9,8]],"date-time":"2020-09-08T00:00:00Z","timestamp":1599523200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J. Imaging"],"abstract":"<jats:p>Convolution neural networks usually require large labeled data-sets to construct accurate models. However, in many real-world scenarios, such as global illumination, labeling data are a time-consuming and costly human intelligent task. Semi-supervised learning methods leverage this issue by making use of a small labeled data-set and a larger set of unlabeled data. In this paper, our contributions focus on the development of a robust algorithm that combines active and deep semi-supervised convolution neural network to reduce labeling workload and to accelerate convergence in case of real-time global illumination. While the theoretical concepts of photo-realistic rendering are well understood, the increased need for the delivery of highly dynamic interactive content in vast virtual environments has increased recently. Particularly, the quality measure of computer-generated images is of great importance. The experiments are conducted on global illumination scenes which contain diverse distortions. Compared with human psycho-visual thresholds, the good consistency between these thresholds and the learning models quality measures can been seen. A comparison has also been made with SVM and other state-of-the-art deep learning models. We do transfer learning by running the convolution base of these models over our image set. Then, we use the output features of the convolution base as input to retrain the parameters of the fully connected layer. The obtained results show that our proposed method provides promising efficiency in terms of precision, time complexity, and optimal architecture.<\/jats:p>","DOI":"10.3390\/jimaging6090091","type":"journal-article","created":{"date-parts":[[2020,9,8]],"date-time":"2020-09-08T09:03:48Z","timestamp":1599555828000},"page":"91","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["On the Use of Deep Active Semi-Supervised Learning for Fast Rendering in Global Illumination"],"prefix":"10.3390","volume":"6","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4252-0819","authenticated-orcid":false,"given":"Ibtissam","family":"Constantin","sequence":"first","affiliation":[{"name":"LaRRIS, Faculty of Sciences, Lebanese University, Fanar, BP 90656 Jdeidet, Lebanon"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7911-1218","authenticated-orcid":false,"given":"Joseph","family":"Constantin","sequence":"additional","affiliation":[{"name":"LaRRIS, Faculty of Sciences, Lebanese University, Fanar, BP 90656 Jdeidet, Lebanon"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Andr\u00e9","family":"Bigand","sequence":"additional","affiliation":[{"name":"LISIC, University of Littoral C\u00f4te d\u2019Opale (ULCO), Calais, BP 719, 62228 Calais CEDEX, France"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2020,9,8]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Wang, B., Meng, X., Xu, Y., and Song, X. (2011, January 15\u201317). Fast Point Based Global Illumination. Proceedings of the 2011 12th International Conference on Computer-Aided Design and Computer Graphics (CAD\/Graphics), Jinan, China.","DOI":"10.1109\/CAD\/Graphics.2011.47"},{"key":"ref_2","first-page":"76","article-title":"Spectral Rendering of Interference Phenomena Caused by Multilayer Films Under Global Illumination Environment","volume":"3","author":"Ikeda","year":"2015","journal-title":"ITE Trans. Media Technol. Appl."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"75","DOI":"10.1111\/cgf.12680","article-title":"Probabilistic connections for bidirectional path tracing","volume":"34","author":"Popov","year":"2015","journal-title":"Comput. Graph. Forum"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Takouachet, N., Delepoulle, S., and Renaud, C. (2007, January 26\u201328). A perceptual stopping condition for global illumination computations. Proceedings of the 23rd Spring Conference on Computer Graphics, Budmerice, Slovakia.","DOI":"10.1145\/2614348.2614357"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Peli, E. (1995). A visual discrimination model for imaging system design and evaluation. Vision Models for Target Detection and Recognition, World Scientific.","DOI":"10.1142\/2641"},{"key":"ref_6","unstructured":"Longhurst, P., and Chalmers, A. (2004, January 8\u201310). User validation of image quality assessment algorithms. Proceedings of the TPCG 04: Theory and Practice of Computer Graphics, Bournemouth, UK."},{"key":"ref_7","first-page":"49","article-title":"Pooling spike neural network for fast rendering in global illumination","volume":"69","author":"Constantin","year":"2019","journal-title":"Neural Comput. Appl."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"82","DOI":"10.1016\/j.neucom.2014.10.090","article-title":"Image Noise Detection in Global Illumination Methods based on FRVM","volume":"64","author":"Constantin","year":"2015","journal-title":"NeuroComputing"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"49","DOI":"10.1016\/j.cag.2017.09.008","article-title":"Perception of noise and Global Illumination: Towards an automatic stopping criterion based on SVM","volume":"69","author":"Takouachet","year":"2017","journal-title":"Comput. Graph."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"368","DOI":"10.1109\/TKDE.2014.2304474","article-title":"Active learning through adaptive heterogeneous ensembling","volume":"27","author":"Lu","year":"2015","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Xu, L., Li, B., and Chen, E. (2012, January 10\u201313). Ensemble pruning via constrained eigenoptimization. Proceedings of the 2012 IEEE 12th International Conference on Data Mining, ICDM, Brussels, Belgium.","DOI":"10.1109\/ICDM.2012.97"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"615","DOI":"10.1016\/j.patcog.2010.09.021","article-title":"A self-trained ensemble with semisupervised SVM: An application to pixel classification of remote sensing imagery","volume":"44","author":"Maulik","year":"2011","journal-title":"Pattern Recognit."},{"key":"ref_13","unstructured":"Bianco, S., Celona, L., Napoletano, P., and Schettin, R. (2016). On the use of Deep Learning for Blind Image quality Assessment. arXiv, 1\u20137."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"130","DOI":"10.1016\/j.patcog.2014.12.009","article-title":"An Active Learning-based SVM Multi-Class Classification Model","volume":"48","author":"Guo","year":"2015","journal-title":"Pattern Recognit."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"109","DOI":"10.1016\/j.cogsys.2017.05.006","article-title":"Active and semi-supervised learning for object detection with imperfect data","volume":"45","author":"Rhee","year":"2017","journal-title":"Cogn. Syst. Res."},{"key":"ref_16","first-page":"245","article-title":"Semi-Supervised Learning Based Social Image Semantic Mining Algorithm","volume":"9","author":"Guangwu","year":"2014","journal-title":"J. Multimed."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"1011","DOI":"10.1016\/j.patcog.2013.07.013","article-title":"Semi-supervised learning for character recognition in historical archive documents","volume":"47","author":"Richarz","year":"2014","journal-title":"J. Pattern Recognit."},{"key":"ref_18","unstructured":"Settles, B. (2009). Active Learning Litterature Survey, University of Wisconsin-Madison."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"563","DOI":"10.1016\/j.knosys.2010.03.015","article-title":"A classification algorithm based on local clusters with a few labeled training examples","volume":"23","author":"Huang","year":"2010","journal-title":"Knowl. Based Syst."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Dornaika, F., Traboulsi, Y.E., and Assoum, A. (2016). Inductive and Flexible Feature Extraction for Semi-Supervised Pattern Categorization. Pattern Recognit.","DOI":"10.1016\/j.patcog.2016.04.024"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.eswa.2016.04.003","article-title":"Improving the performance of inductive learning classifiers through the presentation order of the training patterns","volume":"58","author":"Ruz","year":"2016","journal-title":"Expert Syst. Appl."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"107425","DOI":"10.1016\/j.patcog.2020.107425","article-title":"Semi-supervised elastic manifold embedding with deep learning architecture","volume":"107","author":"Zhu","year":"2020","journal-title":"Pattern Recognit."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"1529","DOI":"10.1109\/TKDE.2005.186","article-title":"Tri-training: Exploiting unlabeled data using three classifiers","volume":"17","author":"Zhou","year":"2005","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"ref_24","first-page":"3546","article-title":"Semisupervised learning with ladder networks","volume":"14","author":"Rasmus","year":"2015","journal-title":"Adv. Neural Inf. Process"},{"key":"ref_25","unstructured":"Tran, P.V. (2019). Semi-Supervised Learning with Self-Supervised Networks. Machine learning. CoRR, Available online: https:\/\/128.84.21.199\/abs\/1906.10343v1."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Zhai, X., Oliver, A., Kolesnikov, A., and Beyer, L. (2019). Self-Supervised Semi-Supervised Learning. Computer Vision and Pattern Recognition. CoRR, Available online: https:\/\/arxiv.org\/pdf\/1905.03670.pdf.","DOI":"10.1109\/ICCV.2019.00156"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"107500","DOI":"10.1016\/j.patcog.2020.107500","article-title":"Semi-supervised learning framework based on statiscal analysis for image set classification","volume":"107","author":"Yan","year":"2020","journal-title":"Pattern Recognit."},{"key":"ref_28","unstructured":"Li, C., and Wu, C. (2010, January 21\u201324). A new semi-supervised support vector machine learning algorithm based on active learning. Proceedings of the International Conference on Future Computer and Communication, Wuhan, China."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"121","DOI":"10.1016\/j.knosys.2013.01.032","article-title":"Combining active learning and semi-supervised learning to construct SVM classifier","volume":"44","author":"Leng","year":"2013","journal-title":"Knowl. Based Syst."},{"key":"ref_30","unstructured":"He, X., Ji, M., and Bao, H. (2009, January 20\u201325). A Unified Active and Semi-supervised Learning Framework for Image Compression. Proceedings of the International Conference on Computer Vision and Pattern Recognition, Miami, FL, USA."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"433","DOI":"10.1016\/j.csl.2009.03.004","article-title":"Active learning and semisupervised learning for speech recognition: A unified framework using the global entropy reduction maximization criterion","volume":"24","author":"Yu","year":"2010","journal-title":"Comput. Speech Lang."},{"key":"ref_32","unstructured":"Li, H., Liao, X., and Carin, L. (2009, January 19\u201324). Active learning for semi-supervised multitask learning. Proceedings of the International Conference on Acoustics, Speech and Signal Processing, Taipei, Taiwan."},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Constantin, J., Constantin, I., Bigand, A., and Hamad, D. (2016, January 24\u201329). Perception of noise in Global Illumination based on Inductive Learning. Proceedings of the 2016 International Joint Conference on Neural Networks (IJCNN), Vancouver, BC, Canada.","DOI":"10.1109\/IJCNN.2016.7727861"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"193","DOI":"10.1007\/978-3-319-07998-1_22","article-title":"CID:IQ A New Image Quality Database","volume":"8509","author":"Liu","year":"2014","journal-title":"Image Signal Process."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"390","DOI":"10.1109\/TIP.2014.2378061","article-title":"CID2013: A Database for Evaluating No-Reference Image Quality Assessment algorithms","volume":"24","author":"Virtanen","year":"2015","journal-title":"IEEE Trans. Image Process."},{"key":"ref_36","unstructured":"Wald, I., Kollig, T., Benthin, C., Keller, A., and Slusalleki, P. (2002, January 26\u201328). Interactive Global Illumination using Fast Ray Tracing. Proceedings of the 13th Eurographics Workshop on Rendering, Pisa, Italy."},{"key":"ref_37","unstructured":"Niederreiter, H., Fang, K., and Hickernell, F. (2002). Efficient Bidirectional Path Tracing by Randomized Quasi-Monte Carlo Integration. Monte Carlo and Quasi-Monte Carlo Methods 2000, Springer."},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Hedman, P., Karras, T., and Lehtinen, J. (2016, January 26\u201328). Sequential Monte Carlo instant radiosity. Proceedings of the 20th ACM SIGGRAPH Symposium on Interactive 3D Graphics and Games, Redmond, WA, USA.","DOI":"10.1145\/2856400.2856406"},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"LeCun","year":"2015","journal-title":"Nature"},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Razavian, A., Azizpour, H., Sullivan, J., and Carlsson, S. (2014, January 23\u201328). CNNfeatures off-the-shelf: An astounding baseline for recognition. Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition CVPR Workshops, Columbus, OH, USA.","DOI":"10.1109\/CVPRW.2014.131"},{"key":"ref_41","first-page":"21","article-title":"Image Enhancement Techniques using Highpass and Lowpass Filters","volume":"109","author":"Makandar","year":"2015","journal-title":"Int. J. Comput. Appl."},{"key":"ref_42","first-page":"425","article-title":"Effect Comparison of Speckle Noise Reduction Filters on 2D-echocardiographic","volume":"6","author":"Dawood","year":"2012","journal-title":"World Acad. Sci. Eng. Technol."},{"key":"ref_43","first-page":"36","article-title":"Deblurring Images using a Wiener Filter","volume":"109","author":"Biswas","year":"2015","journal-title":"Int. J. Comput. Appl."},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"1843","DOI":"10.1007\/s00170-015-7116-0","article-title":"Multi-scale Statistical Signal Processing of Cutting Force in Cutting Tool Condition Monitoring","volume":"90","author":"Gao","year":"2015","journal-title":"Int. J. Adv. Manuf. Technol."},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"476","DOI":"10.1109\/TIFS.2009.2026458","article-title":"Intrinsic Sensor Noise Features for Forensic Analysis on Scanners and Scanned Images","volume":"4","author":"Gou","year":"2009","journal-title":"IEEE Trans. Inf. Forensics Secur."},{"key":"ref_46","doi-asserted-by":"crossref","unstructured":"Fernandez-Maloigne, C., Robert-Inacio, F., and Macaire, L. (2012). Digital Color: Acquisition, Perception, Coding and Rendering, Wiley-ISTE. Chapter 9: Quality Assessment Approaches, 314 Pages.","DOI":"10.1002\/9781118562680"},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"443","DOI":"10.1016\/j.patcog.2013.09.034","article-title":"Active selection of clustering constraints: A sequential approach","volume":"47","author":"Abin","year":"2014","journal-title":"Pattern Recognit."},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"1014","DOI":"10.1109\/TGRS.2010.2072929","article-title":"Batch-mode active learning methods for the interactive classification of remote sensing images","volume":"49","author":"Demir","year":"2011","journal-title":"IEEE Trans. Geosci. Remote. Sens."},{"key":"ref_49","first-page":"45","article-title":"Support Vector Machine Active Learning with Applications to Text Classification","volume":"2","author":"Tong","year":"2000","journal-title":"J. Mach. Learn. Res."},{"key":"ref_50","doi-asserted-by":"crossref","unstructured":"Chapelle, O., Scholkopf, B., and Zien, A. (2006). Semi-Supervised Learning, MIT Press.","DOI":"10.7551\/mitpress\/9780262033589.001.0001"},{"key":"ref_51","doi-asserted-by":"crossref","first-page":"16","DOI":"10.1016\/j.patrec.2019.08.012","article-title":"Semi-supervised learning with connectivity-driven convolutional neural networks","volume":"128","author":"Amorin","year":"2019","journal-title":"Pattern Recognit. Lett."},{"key":"ref_52","unstructured":"Chen, D.G., Wang, H.Y., and Tsang, E.C. (2008, January 12\u201315). Generalized Mercer theorem and its application to feature space related to indefinite kernels. Proceedings of the IEEE International Conference on Machine Learning and Cybernetics, Kunming, China."},{"key":"ref_53","doi-asserted-by":"crossref","unstructured":"Lipton, Z., Elkan, C., and Narayanaswamy, B. (2014). Thresholding Classifiers to Maximize F1 Score. arXiv.","DOI":"10.1007\/978-3-662-44851-9_15"},{"key":"ref_54","unstructured":"Chollet, F. (2017). Deep Learning with Python, Manning Publications."},{"key":"ref_55","doi-asserted-by":"crossref","unstructured":"Falk, M., Grottel, S., Krone, M., and Reina, G. (2016). Interactive GPU-Based Visualization of Large Dynamic Particle Data, Morgan & Claypool.","DOI":"10.1007\/978-3-031-02604-1"}],"container-title":["Journal of Imaging"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2313-433X\/6\/9\/91\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T10:07:54Z","timestamp":1760177274000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2313-433X\/6\/9\/91"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,9,8]]},"references-count":55,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2020,9]]}},"alternative-id":["jimaging6090091"],"URL":"https:\/\/doi.org\/10.3390\/jimaging6090091","relation":{},"ISSN":["2313-433X"],"issn-type":[{"value":"2313-433X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,9,8]]}}}