{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,20]],"date-time":"2024-09-20T16:21:20Z","timestamp":1726849280213},"reference-count":44,"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":"http:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["13-21168,16-19376"],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Graph."],"published-print":{"date-parts":[[2017,8,31]]},"abstract":"Regression-based algorithms have shown to be good at denoising Monte Carlo (MC) renderings by leveraging its inexpensive by-products (e.g., feature buffers). However, when using higher-order models to handle complex cases, these techniques often overfit to noise in the input. For this reason, supervised learning methods have been proposed that train on a large collection of reference examples, but they use explicit filters that limit their denoising ability. To address these problems, we propose a novel, supervised learning approach that allows the filtering kernel to be more complex and general by leveraging a deep convolutional neural network (CNN) architecture. In one embodiment of our framework, the CNN directly predicts the final denoised pixel value as a highly non-linear combination of the input features. In a second approach, we introduce a novel, kernel-prediction network which uses the CNN to estimate the local weighting kernels used to compute each denoised pixel from its neighbors. We train and evaluate our networks on production data and observe improvements over state-of-the-art MC denoisers, showing that our methods generalize well to a variety of scenes. We conclude by analyzing various components of our architecture and identify areas of further research in deep learning for MC denoising.<\/jats:p>","DOI":"10.1145\/3072959.3073708","type":"journal-article","created":{"date-parts":[[2017,7,21]],"date-time":"2017-07-21T12:24:07Z","timestamp":1500639847000},"page":"1-14","update-policy":"http:\/\/dx.doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":196,"title":["Kernel-predicting convolutional networks for denoising Monte Carlo renderings"],"prefix":"10.1145","volume":"36","author":[{"given":"Steve","family":"Bako","sequence":"first","affiliation":[{"name":"University of California"}]},{"given":"Thijs","family":"Vogels","sequence":"additional","affiliation":[{"name":"ETH Z\u00fcrich & Disney Research"}]},{"given":"Brian","family":"Mcwilliams","sequence":"additional","affiliation":[{"name":"Disney Research"}]},{"given":"Mark","family":"Meyer","sequence":"additional","affiliation":[{"name":"Pixar Animation Studios"}]},{"given":"Jan","family":"Nov\u00e1K","sequence":"additional","affiliation":[{"name":"Disney Research"}]},{"given":"Alex","family":"Harvill","sequence":"additional","affiliation":[{"name":"Pixar Animation Studios"}]},{"given":"Pradeep","family":"Sen","sequence":"additional","affiliation":[{"name":"University of California"}]},{"given":"Tony","family":"Derose","sequence":"additional","affiliation":[{"name":"Pixar Animation Studios"}]},{"given":"Fabrice","family":"Rousselle","sequence":"additional","affiliation":[{"name":"Disney Research"}]}],"member":"320","published-online":{"date-parts":[[2017,7,20]]},"reference":[{"key":"e_1_2_1_1_1","unstructured":"Mart\u00edn Abadi Ashish Agarwal Paul Barham and others. 2015. TensorFlow: Large-Scale Machine Learning on Heterogeneous Systems. (2015). http:\/\/tensorflow.org\/Softwareavailablefromtensorflow.org. Mart\u00edn Abadi Ashish Agarwal Paul Barham and others. 2015. TensorFlow: Large-Scale Machine Learning on Heterogeneous Systems. (2015). http:\/\/tensorflow.org\/Softwareavailablefromtensorflow.org."},{"key":"e_1_2_1_2_1","volume-title":"Neural Taylor Approximations: Convergence and Exploration in Rectifier Networks. arXiv preprint arXiv:1611.02345","author":"Balduzzi David","year":"2016","unstructured":"David Balduzzi , Brian McWilliams , and Tony Butler-Yeoman . 2016. Neural Taylor Approximations: Convergence and Exploration in Rectifier Networks. arXiv preprint arXiv:1611.02345 ( 2016 ). David Balduzzi, Brian McWilliams, and Tony Butler-Yeoman. 2016. Neural Taylor Approximations: Convergence and Exploration in Rectifier Networks. arXiv preprint arXiv:1611.02345 (2016)."},{"key":"e_1_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-8659.2011.01996.x"},{"key":"e_1_2_1_4_1","volume-title":"https:\/\/benedikt-bitterli.me\/resources\/","author":"Bitterli Benedikt","year":"2016","unstructured":"Benedikt Bitterli . 2016. Rendering Resources . ( 2016 ). https:\/\/benedikt-bitterli.me\/resources\/ . Benedikt Bitterli. 2016. Rendering Resources. (2016). https:\/\/benedikt-bitterli.me\/resources\/."},{"key":"e_1_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.12954"},{"key":"e_1_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1137\/040616024"},{"key":"e_1_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247952"},{"key":"e_1_2_1_8_1","volume-title":"Interactive Reconstruction of Noisy Monte Carlo Image Sequences using a Recurrent Autoencoder. ACM Trans. Graph. (Proc. SIGGRAPH)","author":"Chaitanya Chakravarty R. A.","year":"2017","unstructured":"Chakravarty R. A. Chaitanya , Anton Kaplanyan , Christoph Schied , Marco Salvi , Aaron Lefohn , Derek Nowrouzezahrai , and Timo Aila . 2017. Interactive Reconstruction of Noisy Monte Carlo Image Sequences using a Recurrent Autoencoder. ACM Trans. Graph. (Proc. SIGGRAPH) ( 2017 ). Chakravarty R. A. Chaitanya, Anton Kaplanyan, Christoph Schied, Marco Salvi, Aaron Lefohn, Derek Nowrouzezahrai, and Timo Aila. 2017. Interactive Reconstruction of Noisy Monte Carlo Image Sequences using a Recurrent Autoencoder. ACM Trans. Graph. (Proc. SIGGRAPH) (2017)."},{"key":"e_1_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/37402.37414"},{"key":"e_1_2_1_10_1","doi-asserted-by":"crossref","unstructured":"Kostadin Dabov Alessandro Foi Vladimir Katkovnik and Karen Egiazarian. 2006. Image Denoising with Block-Matching and 3D Filtering. (2006). Kostadin Dabov Alessandro Foi Vladimir Katkovnik and Karen Egiazarian. 2006. Image Denoising with Block-Matching and 3D Filtering. (2006).","DOI":"10.1117\/12.643267"},{"key":"e_1_2_1_11_1","volume-title":"The Elements of Statistical Learning","author":"Friedman Jerome","unstructured":"Jerome Friedman , Trevor Hastie , and Robert Tibshirani . 2001. The Elements of Statistical Learning . Vol. 1 . Springer series in statistics Springer , Berlin. Jerome Friedman, Trevor Hastie, and Robert Tibshirani. 2001. The Elements of Statistical Learning. Vol. 1. Springer series in statistics Springer, Berlin."},{"key":"e_1_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/2980179.2982399"},{"key":"e_1_2_1_13_1","volume-title":"Understanding the Difficulty of Training Deep Feedforward Neural Networks. In International conference on artificial intelligence and statistics. 249--256","author":"Glorot Xavier","year":"2010","unstructured":"Xavier Glorot and Yoshua Bengio . 2010 . Understanding the Difficulty of Training Deep Feedforward Neural Networks. In International conference on artificial intelligence and statistics. 249--256 . Xavier Glorot and Yoshua Bengio. 2010. Understanding the Difficulty of Training Deep Feedforward Neural Networks. In International conference on artificial intelligence and statistics. 249--256."},{"key":"e_1_2_1_14_1","volume-title":"Silencing the Noise on Elysium. In ACM SIGGRAPH 2014 Talks (SIGGRAPH '14)","author":"Goddard Luke","year":"2014","unstructured":"Luke Goddard . 2014 . Silencing the Noise on Elysium. In ACM SIGGRAPH 2014 Talks (SIGGRAPH '14) . ACM, New York, NY, USA, Article 38, 1 pages. Luke Goddard. 2014. Silencing the Noise on Elysium. In ACM SIGGRAPH 2014 Talks (SIGGRAPH '14). ACM, New York, NY, USA, Article 38, 1 pages."},{"key":"e_1_2_1_15_1","volume-title":"Deep Residual Learning for Image Recognition. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR). http:\/\/arxiv.org\/abs\/1512","author":"He Kaiming","year":"2016","unstructured":"Kaiming He , Xiangyu Zhang , Shaoqing Ren , and Jian Sun . 2016 . Deep Residual Learning for Image Recognition. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR). http:\/\/arxiv.org\/abs\/1512 .03385 Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. 2016. Deep Residual Learning for Image Recognition. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR). http:\/\/arxiv.org\/abs\/1512.03385"},{"key":"e_1_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/15886.15902"},{"key":"e_1_2_1_17_1","volume-title":"Article 122 (July","author":"Kalantari Nima Khademi","year":"2015","unstructured":"Nima Khademi Kalantari , Steve Bako , and Pradeep Sen . 2015. A Machine Learning Approach for Filtering Monte Carlo Noise. 34, 4 , Article 122 (July 2015 ), 12 pages. Nima Khademi Kalantari, Steve Bako, and Pradeep Sen. 2015. A Machine Learning Approach for Filtering Monte Carlo Noise. 34, 4, Article 122 (July 2015), 12 pages."},{"key":"e_1_2_1_18_1","volume-title":"Removing the Noise in Monte Carlo Rendering with General Image Denoising Algorithms. 32, 2pt1","author":"Kalantari Nima Khademi","year":"2013","unstructured":"Nima Khademi Kalantari and Pradeep Sen . 2013. Removing the Noise in Monte Carlo Rendering with General Image Denoising Algorithms. 32, 2pt1 ( 2013 ), 93--102. Nima Khademi Kalantari and Pradeep Sen. 2013. Removing the Noise in Monte Carlo Rendering with General Image Denoising Algorithms. 32, 2pt1 (2013), 93--102."},{"key":"e_1_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/2776880.2792699"},{"key":"e_1_2_1_20_1","volume-title":"Kingma and Jimmy Ba","author":"Diederik","year":"2014","unstructured":"Diederik P. Kingma and Jimmy Ba . 2014 . Adam : A Method for Stochastic Optimization. CoRR abs\/1412.6980 (2014). http:\/\/arxiv.org\/abs\/1412.6980 Diederik P. Kingma and Jimmy Ba. 2014. Adam: A Method for Stochastic Optimization. CoRR abs\/1412.6980 (2014). http:\/\/arxiv.org\/abs\/1412.6980"},{"key":"e_1_2_1_21_1","volume-title":"Auto-Encoding Variational Bayes. In International Conference on Learning Representations.","author":"Kingma Diederik P","year":"2013","unstructured":"Diederik P Kingma and Max Welling . 2013 . Auto-Encoding Variational Bayes. In International Conference on Learning Representations. Diederik P Kingma and Max Welling. 2013. Auto-Encoding Variational Bayes. In International Conference on Learning Representations."},{"key":"e_1_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"key":"e_1_2_1_23_1","volume-title":"Photo-Realistic Single Image Super-Resolution using a Generative Adversarial Network. arXiv preprint arXiv:1609.04802","author":"Ledig Christian","year":"2016","unstructured":"Christian Ledig , Lucas Theis , Ferenc Husz\u00e1r , Jose Caballero , Andrew Cunningham , Alejandro Acosta , Andrew Aitken , Alykhan Tejani , Johannes Totz , Zehan Wang , and others. 2016. Photo-Realistic Single Image Super-Resolution using a Generative Adversarial Network. arXiv preprint arXiv:1609.04802 ( 2016 ). Christian Ledig, Lucas Theis, Ferenc Husz\u00e1r, Jose Caballero, Andrew Cunningham, Alejandro Acosta, Andrew Aitken, Alykhan Tejani, Johannes Totz, Zehan Wang, and others. 2016. Photo-Realistic Single Image Super-Resolution using a Generative Adversarial Network. arXiv preprint arXiv:1609.04802 (2016)."},{"key":"e_1_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/2366145.2366213"},{"key":"e_1_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/318009.318015"},{"key":"e_1_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/2641762"},{"key":"e_1_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.12004"},{"key":"e_1_2_1_28_1","volume-title":"Adaptive Polynomial Rendering. To appear in ACM Trans. Graph. (Proc. SIGGRAPH)","author":"Moon Bochang","year":"2016","unstructured":"Bochang Moon , Steven McDonagh , Kenny Mitchell , and Markus Gross . 2016. Adaptive Polynomial Rendering. To appear in ACM Trans. Graph. (Proc. SIGGRAPH) ( 2016 ), 10. Bochang Moon, Steven McDonagh, Kenny Mitchell, and Markus Gross. 2016. Adaptive Polynomial Rendering. To appear in ACM Trans. Graph. (Proc. SIGGRAPH) (2016), 10."},{"key":"e_1_2_1_29_1","volume-title":"Wavenet: A Generative Model for Raw Audio. arXiv preprint arXiv:1609.03499","author":"van den Oord Aaron","year":"2016","unstructured":"Aaron van den Oord , Sander Dieleman , Heiga Zen , Karen Simonyan , Oriol Vinyals , Alex Graves , Nal Kalchbrenner , Andrew Senior , and Koray Kavukcuoglu . 2016 . Wavenet: A Generative Model for Raw Audio. arXiv preprint arXiv:1609.03499 (2016). Aaron van den Oord, Sander Dieleman, Heiga Zen, Karen Simonyan, Oriol Vinyals, Alex Graves, Nal Kalchbrenner, Andrew Senior, and Koray Kavukcuoglu. 2016. Wavenet: A Generative Model for Raw Audio. arXiv preprint arXiv:1609.03499 (2016)."},{"key":"e_1_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/2024156.2024193"},{"key":"e_1_2_1_31_1","volume-title":"Article 195 (Nov.","author":"Rousselle Fabrice","year":"2012","unstructured":"Fabrice Rousselle , Claude Knaus , and Matthias Zwicker . 2012. Adaptive Rendering with Non-local Means Filtering. 31, 6 , Article 195 (Nov. 2012 ), 11 pages. Fabrice Rousselle, Claude Knaus, and Matthias Zwicker. 2012. Adaptive Rendering with Non-local Means Filtering. 31, 6, Article 195 (Nov. 2012), 11 pages."},{"key":"e_1_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.12219"},{"key":"e_1_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/192161.192189"},{"key":"e_1_2_1_34_1","volume-title":"Weight Normalization: A Simple Reparameterization to Accelerate Training of Deep Neural Networks. In Adv in Neural Information Processing Systems (NIPS).","author":"Salimans Tim","year":"2016","unstructured":"Tim Salimans and Diederik P Kingma . 2016 . Weight Normalization: A Simple Reparameterization to Accelerate Training of Deep Neural Networks. In Adv in Neural Information Processing Systems (NIPS). Tim Salimans and Diederik P Kingma. 2016. Weight Normalization: A Simple Reparameterization to Accelerate Training of Deep Neural Networks. In Adv in Neural Information Processing Systems (NIPS)."},{"key":"e_1_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/2167076.2167083"},{"key":"e_1_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/2776880.2792740"},{"key":"e_1_2_1_37_1","volume-title":"Very Deep Convolutional Networks for Large-Scale Image Recognition. arXiv preprint arXiv:1409.1556","author":"Simonyan Karen","year":"2014","unstructured":"Karen Simonyan and Andrew Zisserman . 2014. Very Deep Convolutional Networks for Large-Scale Image Recognition. arXiv preprint arXiv:1409.1556 ( 2014 ). Karen Simonyan and Andrew Zisserman. 2014. Very Deep Convolutional Networks for Large-Scale Image Recognition. arXiv preprint arXiv:1409.1556 (2014)."},{"key":"e_1_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1214\/aos\/1176345632"},{"key":"e_1_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"e_1_2_1_40_1","unstructured":"Junyuan Xie Linli Xu and Enhong Chen. 2012. Image Denoising and Inpainting with Deep Neural Networks. In Advances in Neural Information Processing Systems. 341--349. Junyuan Xie Linli Xu and Enhong Chen. 2012. Image Denoising and Inpainting with Deep Neural Networks. In Advances in Neural Information Processing Systems. 341--349."},{"key":"e_1_2_1_41_1","volume-title":"Deep Edge Guided Recurrent Residual Learning for Image Super-Resolution. CoRR abs\/1604.08671","author":"Yang Wenhan","year":"2016","unstructured":"Wenhan Yang , Jiashi Feng , Jianchao Yang , Fang Zhao , Jiaying Liu , Zongming Guo , and Shuicheng Yan . 2016. Deep Edge Guided Recurrent Residual Learning for Image Super-Resolution. CoRR abs\/1604.08671 ( 2016 ). http:\/\/arxiv.org\/abs\/1604.08671 Wenhan Yang, Jiashi Feng, Jianchao Yang, Fang Zhao, Jiaying Liu, Zongming Guo, and Shuicheng Yan. 2016. Deep Edge Guided Recurrent Residual Learning for Image Super-Resolution. CoRR abs\/1604.08671 (2016). http:\/\/arxiv.org\/abs\/1604.08671"},{"key":"e_1_2_1_42_1","volume-title":"Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising. arXiv preprint arXiv:1608.03981","author":"Zhang Kai","year":"2016","unstructured":"Kai Zhang , Wangmeng Zuo , Yunjin Chen , Deyu Meng , and Lei Zhang . 2016. Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising. arXiv preprint arXiv:1608.03981 ( 2016 ). Kai Zhang, Wangmeng Zuo, Yunjin Chen, Deyu Meng, and Lei Zhang. 2016. Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising. arXiv preprint arXiv:1608.03981 (2016)."},{"key":"e_1_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.12685"},{"key":"e_1_2_1_44_1","volume-title":"Recent Advances in Adaptive Sampling and Reconstruction for Monte Carlo Rendering. 34, 2 (May","author":"Zwicker Matthias","year":"2015","unstructured":"Matthias Zwicker , Wojciech Jarosz , Jaakko Lehtinen , Bochang Moon , Ravi Ramamoorthi , Fabrice Rousselle , Pradeep Sen , Cyril Soler , and Sung-Eui Yoon . 2015. Recent Advances in Adaptive Sampling and Reconstruction for Monte Carlo Rendering. 34, 2 (May 2015 ), 667--681. Matthias Zwicker, Wojciech Jarosz, Jaakko Lehtinen, Bochang Moon, Ravi Ramamoorthi, Fabrice Rousselle, Pradeep Sen, Cyril Soler, and Sung-Eui Yoon. 2015. Recent Advances in Adaptive Sampling and Reconstruction for Monte Carlo Rendering. 34, 2 (May 2015), 667--681."}],"container-title":["ACM Transactions on Graphics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3072959.3073708","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3072959.3073708","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,4]],"date-time":"2023-09-04T15:36:03Z","timestamp":1693841763000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3072959.3073708"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,7,20]]},"references-count":44,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2017,8,31]]}},"alternative-id":["10.1145\/3072959.3073708"],"URL":"https:\/\/doi.org\/10.1145\/3072959.3073708","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"}}]}}