{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T02:52:18Z","timestamp":1760151138082,"version":"build-2065373602"},"reference-count":32,"publisher":"MDPI AG","issue":"2","license":[{"start":{"date-parts":[[2022,2,16]],"date-time":"2022-02-16T00:00:00Z","timestamp":1644969600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Jilin Provincial Science &amp;Technology Development Program of China","award":["20190302113GX"],"award-info":[{"award-number":["20190302113GX"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Symmetry"],"abstract":"<jats:p>In this paper, we present a denoising network composed of a kernel prediction network and a deep generative adversarial network to construct an end-to-end overall network structure. The network structure consists of three parts: the Kernel Prediction Network (KPN), the Deep Generation Adversarial Network (DGAN), and the image reconstruction model. The kernel prediction network model takes the auxiliary feature information image as the input, passes through the source information encoder, the feature information encoder, and the kernel predictor, and finally generates a prediction kernel for each pixel. The generated adversarial network model is divided into two parts: the generator model and the multiscale discriminator model. The generator model takes the noisy Monte Carlo-rendered image as the input, passes through the symmetric encoder\u2013decoder structure and the residual block structure, and finally outputs the rendered image with preliminary denoising. Then, the prediction kernel and the preliminarily denoised rendered image is sent to the image reconstruction model for reconstruction, and the prediction kernel is applied to the preliminarily denoised rendered image to obtain a preliminarily reconstructed result image. To further improve the quality of the result and to be more robust, the initially reconstructed rendered image undergoes four iterations of filtering for further denoising. Finally, after four iterations of the image reconstruction model, the final denoised image is presented as the output. This denoised image is applied to the loss function. We compared the results from our approach with state-of-the-art results by using the structural similarity index (SSIM) values and peak signal-to-noise ratio (PSNR) values, and we reported a better performance.<\/jats:p>","DOI":"10.3390\/sym14020395","type":"journal-article","created":{"date-parts":[[2022,2,16]],"date-time":"2022-02-16T20:28:59Z","timestamp":1645043339000},"page":"395","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["DGAN-KPN: Deep Generative Adversarial Network and Kernel Prediction Network for Denoising MC Renderings"],"prefix":"10.3390","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5446-7859","authenticated-orcid":false,"given":"Ahmed Mustafa Taha","family":"Alzbier","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, Changchun University of Science and Technology, Changchun 130022, China"},{"name":"School of Computer and Information Technology, Omdurman Islamic University, Omdurman 382, Sudan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chunyi","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Changchun University of Science and Technology, Changchun 130022, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2022,2,16]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Pathak, D., Krahenbuhl, P., Donahue, J., Darrell, T., and Efros, A.A. (2016, January 27\u201330). Context Encoders: Feature Learning by Inpainting. Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA. Available online: https:\/\/doi.ieeecomputersociety.org\/10.1109\/CVPR.2016.278.","DOI":"10.1109\/CVPR.2016.278"},{"key":"ref_2","unstructured":"Brabandere, B.D., Jia, X., Tuytelaars, T., and Gool, L.V. (2016, January 5\u201310). Dynamic filter networks. Proceedings of the 30th International Conference on Neural Information Processing Systems, Barcelona, Spain. Available online: https:\/\/dl.acm.org\/doi\/10.5555\/3157096.3157171."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3072959.3073708","article-title":"Kernel-predicting convolutional networks for denoising Monte Carlo renderings","volume":"36","author":"Bako","year":"2017","journal-title":"ACM Trans. Graph."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3197517.3201388","article-title":"Denoising with kernel prediction and asymmetric loss functions","volume":"37","author":"Vogels","year":"2018","journal-title":"ACM Trans. Graph."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27\u201330). Deep Residual Learning for Image Recognition. Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Mildenhall, B., Barron, J.T., Chen, J., Sharlet, D., Ng, R., and Carroll, R. (2018, January 18\u201323). Burst Denoising with Kernel Prediction Networks. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City, UT, USA. Available online: https:\/\/arxiv.org\/abs\/1712.02327.","DOI":"10.1109\/CVPR.2018.00265"},{"key":"ref_7","first-page":"1","article-title":"Image Restoration Using Very Deep Convolutional Encoder-Decoder Networks with Symmetric Skip Connections","volume":"2","author":"Mao","year":"2016","journal-title":"Comput. Vis. Pattern Recognit."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"125","DOI":"10.1145\/3306346.3322954","article-title":"Sample-based Monte Carlo denoising using a kernel-splatting network","volume":"38","author":"Gharbi","year":"2019","journal-title":"ACM Trans. Graph."},{"key":"ref_9","unstructured":"Goodfellow, I. (2016). NIPS 2016 Tutorial: Generative Adversarial Networks. arXiv, Available online: http:\/\/arxiv.org\/pdf\/1701.00160.pdf."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Isola, P., Zhu, J., Zhou, T., and Efros, A.A. (2017, January 21\u201326). Image-to-Image Translation with Conditional Adversarial Networks. Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.632"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Chen, Q., and Koltun, V. (2017, January 22\u201329). Photographic Image Synthesis with Cascaded Refinement Networks. Proceedings of the International Conference on Computer Vision (ICCV 2017), Venice, Italy. Available online: https:\/\/arxiv.org\/abs\/1707.09405.","DOI":"10.1109\/ICCV.2017.168"},{"key":"ref_12","unstructured":"Dosovitskiy, A., and Brox, T. (2016, January 5\u201310). Generating images with perceptual similarity metrics based on deep networks. Proceedings of the 30th International Conference on Neural Information Processing Systems, Barcelona, Spain."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Gatys, L.A., Ecker, A.S., and Bethge, M. (2016, January 27\u201330). Image Style Transfer Using Convolutional Neural Networks. Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.265"},{"key":"ref_14","first-page":"694","article-title":"Perceptual Losses for Real-Time Style Transfer and Super-Resolution","volume":"9906","author":"Johnson","year":"2016","journal-title":"Comput. Vis. Pattern Recognit."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"829","DOI":"10.1007\/s00371-018-1550-6","article-title":"Point-based rendering enhancement via deep learning","volume":"34","author":"Bui","year":"2018","journal-title":"Vis. Comput."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3355089.3356504","article-title":"Adversarial Monte Carlo Denoising with Conditioned Auxiliary Feature Modulation","volume":"38","author":"Xu","year":"2019","journal-title":"ACM Trans. Graph."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"1123","DOI":"10.1007\/s11390-019-1964-2","article-title":"DEMC: A Deep Dual-Encoder Network for Denoising Monte Carlo Rendering","volume":"34","author":"Yang","year":"2019","journal-title":"J. Comput. Sci. Technol."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1111\/cgf.14049","article-title":"Neural Denoising with Layer Embeddings","volume":"39","author":"Munkberg","year":"2020","journal-title":"Comput. Graph. Forum"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Lu, Y., Xie, N., and Shen, H.T. (2020, January 1\u20139). DMCR-GAN: Adversarial Denoising for Monte Carlo Renderings with Residual Attention Networks and Hierarchical Features Modulation of Auxiliary Buffers. Proceedings of the SIGGRAPH Asia 2020 Technical Communications, Virtual Event, Korea.","DOI":"10.1145\/3410700.3425426"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3478513.3480504","article-title":"Monte Carlo denoising via auxiliary feature guided self-attention","volume":"40","author":"Yu","year":"2021","journal-title":"ACM Trans. Graph."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Marin\u010d, T., Srinivasan, V., G\u00fcl, S., Hellge, C., and Samek, W. (2019, January 22\u201325). Multi-Kernel Prediction Networks for Denoising of Burst Images. Proceedings of the 2019 IEEE International Conference on Image Processing (ICIP), Taipei, Taiwan.","DOI":"10.1109\/ICIP.2019.8803335"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3072959.3073601","article-title":"Interactive reconstruction of Monte Carlo image sequences using a recurrent denoising autoencoder","volume":"36","author":"Chaitanya","year":"2017","journal-title":"ACM Trans. Graph."},{"key":"ref_23","unstructured":"Goodfellow, I.J., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., and Bengio, Y. (2014, January 8\u201313). Generative adversarial nets. Proceedings of the 27th International Conference on Neural Information Processing Systems\u2014Volume 2, Montreal, QC, Canada. Available online: https:\/\/dl.acm.org\/doi\/10.5555\/2969033.2969125."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"2983","DOI":"10.1109\/LCOMM.2021.3091800","article-title":"Noise Learning Based Denoising Autoencoder","volume":"25","author":"Lee","year":"2021","journal-title":"IEEE Commun. Lett."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"7","DOI":"10.1186\/s42492-019-0016-7","article-title":"Brief review of image denoising techniques","volume":"2","author":"Fan","year":"2019","journal-title":"Vis. Comput. Ind. Biomed. Art"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Hor\u00e9, A., and Ziou, D. (2010, January 23\u201326). Image Quality Metrics: PSNR vs. SSIM. Proceedings of the 2010 20th International Conference on Pattern Recognition, Istanbul, Turkey.","DOI":"10.1109\/ICPR.2010.579"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"267","DOI":"10.1145\/566654.566575","article-title":"Photographic tone reproduction for digital images","volume":"21","author":"Reinhard","year":"2002","journal-title":"ACM Trans. Graph."},{"key":"ref_28","unstructured":"Bitterli, B. (2021, November 01). Rendering Resources. Available online: https:\/\/benedikt-bitterli.me\/resources\/."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"307","DOI":"10.1561\/2200000056","article-title":"An Introduction to Variational Autoencoders","volume":"12","author":"Kingma","year":"2019","journal-title":"Found. Trends Mach. Learn."},{"key":"ref_30","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":"Zhou","year":"2004","journal-title":"IEEE Trans. Image Process."},{"key":"ref_31","unstructured":"Glorot, X., and Bengio, Y. (2010, January 13\u201315). Understanding the difficulty of training deep feedforward neural networks. Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics, Sardinia, Italy. Available online: http:\/\/proceedings.mlr.press\/v9\/glorot10a.html."},{"key":"ref_32","unstructured":"Bitterli, B. (2021, November 01). The Tungsten Renderer. Available online: https:\/\/benedikt-bitterli.me\/tungsten.html."}],"container-title":["Symmetry"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2073-8994\/14\/2\/395\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T22:21:07Z","timestamp":1760134867000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2073-8994\/14\/2\/395"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,2,16]]},"references-count":32,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2022,2]]}},"alternative-id":["sym14020395"],"URL":"https:\/\/doi.org\/10.3390\/sym14020395","relation":{},"ISSN":["2073-8994"],"issn-type":[{"type":"electronic","value":"2073-8994"}],"subject":[],"published":{"date-parts":[[2022,2,16]]}}}