“Weakly-supervised contrastive learning in path manifold for Monte Carlo image reconstruction” by Cho, Huo and Yoon

  • ©In-Young Cho, Yuchi Huo, and Sung-Eui Yoon




    Weakly-supervised contrastive learning in path manifold for Monte Carlo image reconstruction



    Image-space auxiliary features such as surface normal have significantly contributed to the recent success of Monte Carlo (MC) reconstruction networks. However, path-space features, another essential piece of light propagation, have not yet been sufficiently explored. Due to the curse of dimensionality, information flow between a regression loss and high-dimensional path-space features is sparse, leading to difficult training and inefficient usage of path-space features in a typical reconstruction framework. This paper introduces a contrastive manifold learning framework to utilize path-space features effectively. The proposed framework employs weakly-supervised learning that converts reference pixel colors to dense pseudo labels for light paths. A convolutional path-embedding network then induces a low-dimensional manifold of paths by iteratively clustering intra-class embeddings, while discriminating inter-class embeddings using gradient descent. The proposed framework facilitates path-space exploration of reconstruction networks by extracting low-dimensional yet meaningful embeddings within the features. We apply our framework to the recent image- and sample-space models and demonstrate considerable improvements, especially on the sample space. The source code is available at https://github.com/Mephisto405/WCMC.


    1. Martín Abadi and et al. 2016. Tensorflow: Large-scale machine learning on heterogeneous distributed systems. arXiv preprint arXiv:1603.04467 (2016).Google Scholar
    2. Jonghee Back, Sung-Eui Yoon, and Bochang Moon. 2018. Feature Generation for Adaptive Gradient-Domain Path Tracing. Computer Graphics Forum 37, 7 (2018), 65–74.Google ScholarCross Ref
    3. Steve Bako, Mark Meyer, Tony DeRose, and Pradeep Sen. 2019. Offline deep importance sampling for Monte Carlo path tracing. In Computer Graphics Forum, Vol. 38. Wiley Online Library, 527–542.Google Scholar
    4. Steve Bako, Thijs Vogels, Brian Mcwilliams, Mark Meyer, Jan Novák, Alex Harvill, Pradeep Sen, Tony Derose, and Fabrice Rousselle. 2017. Kernel-predicting convolutional networks for denoising Monte Carlo renderings. ACM Transactions on Graphics (TOG) 36, 4 (2017), 97.Google ScholarDigital Library
    5. Elena Balashova, Amit H. Bermano, Vladimir G. Kim, Stephen DiVerdi, Aaron Hertzmann, and Thomas Funkhouser. 2019. Learning A Stroke-Based Representation for Fonts. Computer Graphics Forum 38, 1 (2019), 429–442.Google ScholarCross Ref
    6. Benedikt Bitterli. 2016. Rendering resources. https://benedikt-bitterli.me/resources/.Google Scholar
    7. Leo Breiman. 2001. Random forests. Machine learning 45, 1 (2001), 5–32.Google ScholarDigital Library
    8. Antoni Buades, Bartomeu Coll, and Jean-Michel Morel. 2005. A review of image denoising algorithms, with a new one. Multiscale Modeling & Simulation 4, 2 (2005), 490–530.Google ScholarCross Ref
    9. Chakravarty R Alla Chaitanya, Anton S Kaplanyan, Christoph Schied, Marco Salvi, Aaron Lefohn, Derek Nowrouzezahrai, and Timo Aila. 2017. Interactive reconstruction of Monte Carlo image sequences using a recurrent denoising autoencoder. ACM Transactions on Graphics (TOG) 36, 4 (2017), 98.Google Scholar
    10. Shixing Chen, Caojin Zhang, Ming Dong, Jialiang Le, and Mike Rao. 2017. Using Ranking-CNN for Age Estimation. In CVPR.Google Scholar
    11. Ting Chen, Simon Kornblith, Mohammad Norouzi, and Geoffrey Hinton. 2020. A simple framework for contrastive learning of visual representations. In International conference on machine learning. PMLR, 1597–1607.Google Scholar
    12. Mauricio Delbracio, Pablo Musé, Antoni Buades, Julien Chauvier, Nicholas Phelps, and Jean-Michel Morel. 2014. Boosting monte carlo rendering by ray histogram fusion. ACM Transactions on Graphics (TOG) 33, 1 (2014), 1–15.Google ScholarDigital Library
    13. Jiankang Deng, Jia Guo, Niannan Xue, and Stefanos Zafeiriou. 2019. ArcFace: Additive Angular Margin Loss for Deep Face Recognition. In CVPR.Google Scholar
    14. Elmar Eisemann and Frédo Durand. 2004. Flash photography enhancement via intrinsic relighting. ACM transactions on graphics (TOG) 23, 3 (2004), 673–678.Google Scholar
    15. Michaël Gharbi, Gaurav Chaurasia, Sylvain Paris, and Frédo Durand. 2016. Deep joint demosaicking and denoising. ACM Transactions on Graphics (TOG) 35, 6 (2016), 1–12.Google ScholarDigital Library
    16. Michaël Gharbi, Tzu-Mao Li, Miika Aittala, Jaakko Lehtinen, and Frédo Durand. 2019. Sample-based Monte Carlo denoising using a kernel-splatting network. ACM Transactions on Graphics (TOG) 38, 4 (2019), 1–12.Google ScholarDigital Library
    17. Xavier Glorot and Yoshua Bengio. 2010. Understanding the difficulty of training deep feedforward neural networks. In Proceedings of the thirteenth international conference on artificial intelligence and statistics. 249–256.Google Scholar
    18. Raia Hadsell, Sumit Chopra, and Yann LeCun. 2006. Dimensionality Reduction by Learning an Invariant Mapping. In CVPR.Google Scholar
    19. Johannes Hanika, Marc Droske, and Luca Fascione. 2015a. Manifold next event estimation. Computer Graphics Forum 34, 4 (2015), 87–97.Google ScholarDigital Library
    20. Johannes Hanika, Anton Kaplanyan, and Carsten Dachsbacher. 2015b. Improved half vector space light transport. Computer Graphics Forum 34, 4 (2015), 65–74.Google ScholarDigital Library
    21. Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. 2015. Delving deep into rectifiers: Surpassing human-level performance on imagenet classification. In CVPR.Google Scholar
    22. Paul S Heckbert. 1990. Adaptive radiosity textures for bidirectional ray tracing. In Computer graphics and interactive techniques.Google Scholar
    23. Gary B. Huang, Manu Ramesh, Tamara Berg, and Erik Learned-Miller. 2007. Labeled Faces in the Wild: A Database for Studying Face Recognition in Unconstrained Environments. Technical Report 07–49. University of Massachusetts, Amherst.Google Scholar
    24. Yuchi Huo, Rui Wang, Ruzahng Zheng, Hualin Xu, Hujun Bao, and Sung-Eui Yoon. 2020. Adaptive Incident Radiance Field Sampling and Reconstruction Using Deep Reinforcement Learning. ACM Transactions on Graphics (TOG) 39, 1 (2020), 1–17.Google ScholarDigital Library
    25. Woobin Im, Sungeun Hong, Sung-Eui Yoon, and Hyun S Yang. 2018. Scale-Varying Triplet Ranking with Classification Loss for Facial Age Estimation. In ACCV. 247–259.Google Scholar
    26. Wenzel Jakob and Steve Marschner. 2012. Manifold exploration: a Markov Chain Monte Carlo technique for rendering scenes with difficult specular transport. ACM Transactions on Graphics (TOG) 31, 4 (2012), 1–13.Google ScholarDigital Library
    27. James T Kajiya. 1986. The rendering equation. In Proceedings of the 13th annual conference on Computer graphics and interactive techniques. 143–150.Google ScholarDigital Library
    28. Nima Khademi Kalantari, Steve Bako, and Pradeep Sen. 2015. A machine learning approach for filtering Monte Carlo noise. ACM Transactions on Graphics (TOG) 34, 4 (2015), 122.Google ScholarDigital Library
    29. Anton S Kaplanyan, Johannes Hanika, and Carsten Dachsbacher. 2014. The natural-constraint representation of the path space for efficient light transport simulation. ACM Transactions on Graphics (TOG) 33, 4 (2014), 1–13.Google ScholarDigital Library
    30. Mahmut Kaya and Hasan şakir Bilge. 2019. Deep metric learning: A survey. Symmetry 11, 9 (2019), 1066.Google ScholarCross Ref
    31. Markus Kettunen, Erik Härkönen, and Jaakko Lehtinen. 2019. Deep convolutional reconstruction for gradient-domain rendering. ACM Transactions on Graphics (TOG) 38, 4 (2019), 1–12.Google ScholarDigital Library
    32. Markus Kettunen, Marco Manzi, Miika Aittala, Jaakko Lehtinen, Frédo Durand, and Matthias Zwicker. 2015. Gradient-domain path tracing. ACM Transactions on Graphics (TOG) 34, 4 (2015), 1–13.Google ScholarDigital Library
    33. Prannay Khosla, Piotr Teterwak, Chen Wang, Aaron Sarna, Yonglong Tian, Phillip Isola, Aaron Maschinot, Ce Liu, and Dilip Krishnan. 2020. Supervised contrastive learning. arXiv preprint arXiv:2004.11362 (2020).Google Scholar
    34. Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014).Google Scholar
    35. Weiheng Lin, Beibei Wang, Jian Yang, Lu Wang, and Ling-Qi Yan. 2021. Path-based Monte Carlo Denoising Using a Three-Scale Neural Network. Computer Graphics Forum (2021).Google Scholar
    36. Laurens van der Maaten and Geoffrey Hinton. 2008. Visualizing data using t-SNE. Journal of machine learning research 9, Nov (2008), 2579–2605.Google Scholar
    37. Bochang Moon, Nathan Carr, and Sung-Eui Yoon. 2014. Adaptive rendering based on weighted local regression. ACM Transactions on Graphics (TOG) 33, 5 (2014), 1–14.Google ScholarDigital Library
    38. Bochang Moon, Jong Yun Jun, JongHyeob Lee, Kunho Kim, Toshiya Hachisuka, and Sung-Eui Yoon. 2013. Robust Image Denoising Using a Virtual Flash Image for Monte Carlo Ray Tracing. Computer Graphics Forum 32, 1 (2013), 139–151.Google ScholarCross Ref
    39. Bochang Moon, Steven McDonagh, Kenny Mitchell, and Markus Gross. 2016. Adaptive polynomial rendering. ACM Transactions on Graphics (TOG) 35, 4 (2016), 40.Google ScholarDigital Library
    40. Thomas Müller, Markus Gross, and Jan Novák. 2017. Practical path guiding for efficient light-transport simulation. In Computer Graphics Forum, Vol. 36. Wiley Online Library, 91–100.Google Scholar
    41. Thomas Müller, Brian McWilliams, Fabrice Rousselle, Markus Gross, and Jan Novák. 2019. Neural importance sampling. ACM Transactions on Graphics (TOG) 38, 5 (2019), 1–19.Google ScholarDigital Library
    42. Jacob Munkberg and Jon Hasselgren. 2020. Neural Denoising with Layer Embeddings. Computer Graphics Forum 39, 4 (2020), 1–12.Google ScholarCross Ref
    43. Steven G. Parker, Heiko Friedrich, David Luebke, Keith Morley, James Bigler, Jared Hoberock, David McAllister, Austin Robison, Andreas Dietrich, Greg Humphreys, Morgan McGuire, and Martin Stich. 2013. GPU Ray Tracing. Commun. ACM 56, 5 (May 2013), 93–101. Google ScholarDigital Library
    44. Adam Paszke, Sam Gross, Soumith Chintala, Gregory Chanan, Edward Yang, Zachary DeVito, Zeming Lin, Alban Desmaison, Luca Antiga, and Adam Lerer. 2017. Automatic differentiation in pytorch. (2017).Google Scholar
    45. Erik Reinhard, Michael Stark, Peter Shirley, and James Ferwerda. 2002. Photographic tone reproduction for digital images. In Proceedings of the 29th annual conference on Computer graphics and interactive techniques. 267–276.Google ScholarDigital Library
    46. Fabrice Rousselle, Marco Manzi, and Matthias Zwicker. 2013. Robust denoising using feature and color information. In Computer Graphics Forum, Vol. 32. Wiley Online Library, 121–130.Google Scholar
    47. David E Rumelhart, Geoffrey E Hinton, and Ronald J Williams. 1986. Learning representations by back-propagating errors. nature 323, 6088 (1986), 533–536.Google Scholar
    48. Yi Sun, Yuheng Chen, Xiaogang Wang, and Xiaoou Tang. 2014. Deep Learning Face Representation by Joint Identification-Verification. In Annual Conference on Neural Information Processing Systems 2014. Montreal, Quebec, Canada, 1988–1996.Google Scholar
    49. Michael Tschannen, Josip Djolonga, Marvin Ritter, Aravindh Mahendran, Neil Houlsby, Sylvain Gelly, and Mario Lucic. 2020. Self-supervised learning of video-induced visual invariances. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 13806–13815.Google ScholarCross Ref
    50. Berk Ulker, Sander Stuijk, Henk Corporaal, and Rob Wijnhoven. 2020. Reviewing inference performance of state-of-the-art deep learning frameworks. In Proceedings of the 23th International Workshop on Software and Compilers for Embedded Systems. 48–53.Google ScholarDigital Library
    51. Thijs Vogels, Fabrice Rousselle, Brian Mcwilliams, Gerhard Röthlin, Alex Harvill, David Adler, Mark Meyer, and Jan Novák. 2018. Denoising with kernel prediction and asymmetric loss functions. ACM Transactions on Graphics (TOG) 37, 4 (2018), 124.Google ScholarDigital Library
    52. Jiří Vorba, Ondřej Karlík, Martin Šik, Tobias Ritschel, and Jaroslav Křivánek. 2014. On-line learning of parametric mixture models for light transport simulation. ACM Transactions on Graphics (TOG) 33, 4 (2014), 1–11.Google ScholarDigital Library
    53. Jian Wang, Feng Zhou, Shilei Wen, Xiao Liu, and Yuanqing Lin. 2017. Deep Metric Learning with Angular Loss. In IEEE International Conference on Computer Vision, ICCV 2017. IEEE Computer Society, Venice, Italy, 2612–2620.Google Scholar
    54. Zhou Wang, Alan C Bovik, Hamid R Sheikh, and Eero P Simoncelli. 2004. Image quality assessment: from error visibility to structural similarity. IEEE transactions on image processing 13, 4 (2004), 600–612.Google ScholarDigital Library
    55. Chao-Yuan Wu, R Manmatha, Alexander J Smola, and Philipp Krahenbuhl. 2017. Sampling matters in deep embedding learning. In Proceedings of the IEEE International Conference on Computer Vision. 2840–2848.Google ScholarCross Ref
    56. Zhirong Wu, Yuanjun Xiong, Stella X Yu, and Dahua Lin. 2018. Unsupervised feature learning via non-parametric instance discrimination. In CVPR.Google Scholar
    57. Bing Xu, Junfei Zhang, Rui Wang, Kun Xu, Yong-Liang Yang, Chuan Li, and Rui Tang. 2019. Adversarial Monte Carlo denoising with conditioned auxiliary feature modulation. ACM Transactions on Graphics (TOG) 38, 6 (2019), 224–1.Google ScholarDigital Library
    58. Tizian Zeltner, Iliyan Georgiev, and Wenzel Jakob. 2020. Specular manifold sampling for rendering high-frequency caustics and glints. ACM Transactions on Graphics (TOG) 39, 4 (2020), 149–1.Google ScholarDigital Library
    59. Quan Zheng and Matthias Zwicker. 2019. Learning to importance sample in primary sample space. In Computer Graphics Forum, Vol. 38. Wiley Online Library, 169–179.Google Scholar
    60. Zhi-Hua Zhou. 2018. A brief introduction to weakly supervised learning. National science review 5, 1 (2018), 44–53.Google Scholar
    61. Henning Zimmer, Fabrice Rousselle, Wenzel Jakob, Oliver Wang, David Adler, Wojciech Jarosz, Olga Sorkine-Hornung, and Alexander Sorkine-Hornung. 2015. Path-space motion estimation and decomposition for robust animation filtering. In Computer Graphics Forum, Vol. 34. Wiley Online Library, 131–142.Google Scholar
    62. Károly Zsolnai-Fehér, Peter Wonka, and Michael Wimmer. 2018. Gaussian Material Synthesis. ACM Transactions on Graphics (TOG) 37, 4, Article 76 (July 2018), 14 pages.Google ScholarDigital Library

ACM Digital Library Publication: