{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T06:08:05Z","timestamp":1784268485491,"version":"3.55.0"},"reference-count":69,"publisher":"Association for Computing Machinery (ACM)","issue":"4","license":[{"start":{"date-parts":[[2017,7,20]],"date-time":"2017-07-20T00:00:00Z","timestamp":1500508800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Graph."],"published-print":{"date-parts":[[2017,8,31]]},"abstract":"<jats:p>We describe a machine learning technique for reconstructing image sequences rendered using Monte Carlo methods. Our primary focus is on reconstruction of global illumination with extremely low sampling budgets at interactive rates. Motivated by recent advances in image restoration with deep convolutional networks, we propose a variant of these networks better suited to the class of noise present in Monte Carlo rendering. We allow for much larger pixel neighborhoods to be taken into account, while also improving execution speed by an order of magnitude. Our primary contribution is the addition of recurrent connections to the network in order to drastically improve temporal stability for sequences of sparsely sampled input images. Our method also has the desirable property of automatically modeling relationships based on auxiliary per-pixel input channels, such as depth and normals. We show significantly higher quality results compared to existing methods that run at comparable speeds, and furthermore argue a clear path for making our method run at realtime rates in the near future.<\/jats:p>","DOI":"10.1145\/3072959.3073601","type":"journal-article","created":{"date-parts":[[2017,7,21]],"date-time":"2017-07-21T12:24:07Z","timestamp":1500639847000},"page":"1-12","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":214,"title":["Interactive reconstruction of Monte Carlo image sequences using a recurrent denoising autoencoder"],"prefix":"10.1145","volume":"36","author":[{"given":"Chakravarty R. Alla","family":"Chaitanya","sequence":"first","affiliation":[{"name":"University of Montreal and McGill University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anton S.","family":"Kaplanyan","sequence":"additional","affiliation":[{"name":"NVIDIA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Christoph","family":"Schied","sequence":"additional","affiliation":[{"name":"NVIDIA and Karlsruhe Institute of Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marco","family":"Salvi","sequence":"additional","affiliation":[{"name":"NVIDIA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aaron","family":"Lefohn","sequence":"additional","affiliation":[{"name":"NVIDIA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Derek","family":"Nowrouzezahrai","sequence":"additional","affiliation":[{"name":"McGill University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Timo","family":"Aila","sequence":"additional","affiliation":[{"name":"NVIDIA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2017,7,20]]},"reference":[{"key":"e_1_2_2_1_1","doi-asserted-by":"crossref","unstructured":"Bako S. Vogels T. McWilliams B. Meyer M. Nov\u00e1k J. Harvill A. Sen P. DeRose T. and Rousselle F. 2017. Kernel-Predicting Convolutional Networks for Denoising Monte Carlo Renderings. ACM Trans. Graph. (2017).  Bako S. Vogels T. McWilliams B. Meyer M. Nov\u00e1k J. Harvill A. Sen P. DeRose T. and Rousselle F. 2017. Kernel-Predicting Convolutional Networks for Denoising Monte Carlo Renderings. ACM Trans. Graph. (2017).","DOI":"10.1145\/3072959.3073708"},{"key":"e_1_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.12511"},{"key":"e_1_2_2_3_1","doi-asserted-by":"crossref","unstructured":"Bauszat P. Eisemann M. and Magnor M. 2011. Guided Image Filtering for Interactive High-quality Global Illumination (Comp. Graph. Forum). 8.  Bauszat P. Eisemann M. and Magnor M. 2011. Guided Image Filtering for Interactive High-quality Global Illumination (Comp. Graph. Forum). 8.","DOI":"10.1111\/j.1467-8659.2011.01996.x"},{"key":"e_1_2_2_4_1","volume-title":"The brigade renderer: A path tracer for real-time games. J. Comp. Games Tech. 8","author":"Bikker J.","year":"2013"},{"key":"e_1_2_2_5_1","doi-asserted-by":"crossref","unstructured":"Bitterli B. Rousselle F. Moon B. Iglesias-Guiti\u00e1n J. A. Adler D. Mitchell K. Jarosz W. and Nov\u00e1k J. 2016. Nonlinearly Weighted First-order Regression for Denoising Monte Carlo Renderings. Comp. Graph. Forum 35 4 (2016).  Bitterli B. Rousselle F. Moon B. Iglesias-Guiti\u00e1n J. A. Adler D. Mitchell K. Jarosz W. and Nov\u00e1k J. 2016. Nonlinearly Weighted First-order Regression for Denoising Monte Carlo Renderings. Comp. Graph. Forum 35 4 (2016).","DOI":"10.1111\/cgf.12954"},{"key":"e_1_2_2_6_1","volume-title":"Proc. High Perf. Graph.","author":"Dammertz H."},{"key":"e_1_2_2_7_1","doi-asserted-by":"crossref","DOI":"10.1145\/54852.378468","volume-title":"The Triangle Processor and Normal Vector Shader: A VLSI System for High Performance Graphics. Proc. SIGGRAPH 22","author":"Deering M.","year":"1988"},{"key":"e_1_2_2_8_1","volume-title":"Lasagne: First release.","author":"Dieleman S.","year":"2015"},{"key":"e_1_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298761"},{"key":"e_1_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/2070781.2024214"},{"key":"e_1_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/1944846.1944849"},{"key":"e_1_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/1531326.1531399"},{"key":"e_1_2_2_13_1","doi-asserted-by":"crossref","unstructured":"Fischer P. Dosovitskiy A. Ilg E. H\u00e4usser P. Hazirbas C. Golkov V. van der Smagt P. Cremers D. and Brox T. 2015. FlowNet: Learning Optical Flow with Convolutional Networks. ArXiv e-prints (2015). arXiv:1504.06852.  Fischer P. Dosovitskiy A. Ilg E. H\u00e4usser P. Hazirbas C. Golkov V. van der Smagt P. Cremers D. and Brox T. 2015. FlowNet: Learning Optical Flow with Convolutional Networks. ArXiv e-prints (2015). arXiv:1504.06852.","DOI":"10.1109\/ICCV.2015.316"},{"key":"e_1_2_2_14_1","volume-title":"Proc. CVPR.","author":"Flynn J."},{"key":"e_1_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/2185520.2185529"},{"key":"e_1_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"e_1_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/355588.365104"},{"key":"e_1_2_2_18_1","volume-title":"Proc. Comp. Arch.","author":"Han S."},{"key":"e_1_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-8659.2011.02054.x"},{"key":"e_1_2_2_20_1","unstructured":"He K. Zhang X. Ren S. and Sun J. 2015a. Deep Residual Learning for Image Recognition. ArXiv e-prints (2015). arXiv:1512.03385.  He K. Zhang X. Ren S. and Sun J. 2015a. Deep Residual Learning for Image Recognition. ArXiv e-prints (2015). arXiv:1512.03385."},{"key":"e_1_2_2_21_1","volume-title":"Proc. IEEE Conf. Comp. Vis.","author":"He K."},{"key":"e_1_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/2776880.2787670"},{"key":"e_1_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/2614028.2615431"},{"key":"e_1_2_2_24_1","volume-title":"Proc. NIPS.","author":"Huang Y."},{"key":"e_1_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/2897824.2925974"},{"key":"e_1_2_2_26_1","volume":"199","author":"Jensen H. W.","journal-title":"J."},{"key":"e_1_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/15922.15902"},{"key":"e_1_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/2766977"},{"key":"e_1_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.12026"},{"key":"e_1_2_2_30_1","unstructured":"Karis B. 2014. High-quality temporal supersampling. In Advances in Real-Time Rendering in Games SIGGRAPH Courses.  Karis B. 2014. High-quality temporal supersampling. In Advances in Real-Time Rendering in Games SIGGRAPH Courses."},{"key":"e_1_2_2_31_1","doi-asserted-by":"crossref","unstructured":"Keller A. Fascione L. Fajardo M. Georgiev I. Christensen P. Hanika J. Eisenacher C. and Nichols G. 2015. The path tracing revolution in the movie industry. SIGGRAPH Courses (2015).  Keller A. Fascione L. Fajardo M. Georgiev I. Christensen P. Hanika J. Eisenacher C. and Nichols G. 2015. The path tracing revolution in the movie industry. SIGGRAPH Courses (2015).","DOI":"10.1145\/2776880.2792699"},{"key":"e_1_2_2_32_1","volume-title":"Adam: A Method for Stochastic Optimization. ArXiv e-prints","author":"Kingma D.","year":"2014"},{"key":"e_1_2_2_33_1","volume-title":"Proc. NIPS.","author":"Krizhevsky A."},{"key":"e_1_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_35"},{"key":"e_1_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"e_1_2_2_36_1","doi-asserted-by":"crossref","unstructured":"Ledig C. Theis L. Huszar F. Caballero J. Aitken A. P. Tejani A. Totz J. Wang Z. and Shi W. 2016. Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network. ArXiv e-prints (2016). arXiv:1609.04802.  Ledig C. Theis L. Huszar F. Caballero J. Aitken A. P. Tejani A. Totz J. Wang Z. and Shi W. 2016. Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network. ArXiv e-prints (2016). arXiv:1609.04802.","DOI":"10.1109\/CVPR.2017.19"},{"key":"e_1_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/38.55149"},{"key":"e_1_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/2185520.2185547"},{"key":"e_1_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/2366145.2366213"},{"key":"e_1_2_2_40_1","volume-title":"International Conference on Machine Learning","volume":"30","author":"Maas A. L."},{"key":"e_1_2_2_41_1","volume-title":"Proc. NIPS. arXiv:1606","author":"Mao X."},{"key":"e_1_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/318009.318015"},{"key":"e_1_2_2_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/2366145.2366182"},{"key":"e_1_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/2461912.2461947"},{"key":"e_1_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/2601097.2601113"},{"key":"e_1_2_2_46_1","unstructured":"Mishkin D. Sergievskiy N. and Matas J. 2016. Systematic evaluation of CNN advances on the ImageNet. ArXiv e-prints (2016). arXiv:1606.02228.  Mishkin D. Sergievskiy N. and Matas J. 2016. Systematic evaluation of CNN advances on the ImageNet. ArXiv e-prints (2016). arXiv:1606.02228."},{"key":"e_1_2_2_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/2766992"},{"key":"e_1_2_2_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/2897824.2925936"},{"key":"e_1_2_2_49_1","doi-asserted-by":"publisher","DOI":"10.1145\/2980179.2982407"},{"key":"e_1_2_2_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/1778765.1778803"},{"key":"e_1_2_2_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.278"},{"key":"e_1_2_2_52_1","unstructured":"Patraucean V. Handa A. and Cipolla R. 2015. Spatio-temporal video autoencoder with differentiable memory. ArXiv e-prints (2015). arXiv:1511.06309.  Patraucean V. Handa A. and Cipolla R. 2015. Spatio-temporal video autoencoder with differentiable memory. ArXiv e-prints (2015). arXiv:1511.06309."},{"key":"e_1_2_2_53_1","volume-title":"Proc. Artificial Intelligence and Statistics. J. of Machine Learning Research 22","author":"Raiko T."},{"key":"e_1_2_2_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2010.2090538"},{"key":"e_1_2_2_55_1","doi-asserted-by":"publisher","DOI":"10.1145\/1572769.1572784"},{"key":"e_1_2_2_56_1","doi-asserted-by":"crossref","unstructured":"Ronneberger O. Fischer P. and Brox T. 2015. U-Net: Convolutional Networks for Biomedical Image Segmentation. 234--241.  Ronneberger O. Fischer P. and Brox T. 2015. U-Net: Convolutional Networks for Biomedical Image Segmentation. 234--241.","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"e_1_2_2_57_1","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.12219"},{"key":"e_1_2_2_58_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2014.09.003"},{"key":"e_1_2_2_60_1","doi-asserted-by":"publisher","DOI":"10.1145\/2167076.2167083"},{"key":"e_1_2_2_61_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.207"},{"key":"e_1_2_2_62_1","doi-asserted-by":"publisher","DOI":"10.1214\/aos\/1176345632"},{"key":"e_1_2_2_63_1","volume-title":"Theano: A Python framework for fast computation of mathematical expressions. ArXiv e-prints","author":"Theano Development Team","year":"2016"},{"key":"e_1_2_2_65_1","volume-title":"Proc. Machine Learning","author":"Vincent P.","year":"2008"},{"key":"e_1_2_2_66_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"e_1_2_2_67_1","doi-asserted-by":"publisher","DOI":"10.1016\/0893-6080(88)90007-X"},{"key":"e_1_2_2_68_1","doi-asserted-by":"publisher","DOI":"10.1145\/2816814"},{"key":"e_1_2_2_69_1","unstructured":"Zhao H. Gallo O. Frosio I. and Kautz J. 2016. Loss Functions for Image Restoration with Neural Networks. IEEE Transactions on Computational Imaging (2016).  Zhao H. Gallo O. Frosio I. and Kautz J. 2016. Loss Functions for Image Restoration with Neural Networks. IEEE Transactions on Computational Imaging (2016)."},{"key":"e_1_2_2_70_1","first-page":"4","volume":"34","author":"Zimmer H.","year":"2015","journal-title":"Robust Animation Filtering. Comp. Graph. Forum"},{"key":"e_1_2_2_71_1","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.12592"}],"container-title":["ACM Transactions on Graphics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3072959.3073601","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3072959.3073601","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T03:37:23Z","timestamp":1750217843000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3072959.3073601"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,7,20]]},"references-count":69,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2017,8,31]]}},"alternative-id":["10.1145\/3072959.3073601"],"URL":"https:\/\/doi.org\/10.1145\/3072959.3073601","relation":{},"ISSN":["0730-0301","1557-7368"],"issn-type":[{"value":"0730-0301","type":"print"},{"value":"1557-7368","type":"electronic"}],"subject":[],"published":{"date-parts":[[2017,7,20]]},"assertion":[{"value":"2017-07-20","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}