“Practical Error Estimation for Denoised Monte Carlo Image Synthesis” – ACM SIGGRAPH HISTORY ARCHIVES

“Practical Error Estimation for Denoised Monte Carlo Image Synthesis”

  • ©

Conference:


Type(s):


Title:

    Practical Error Estimation for Denoised Monte Carlo Image Synthesis

Presenter(s)/Author(s):



Abstract:


    We present a practical error estimation technique for denoised Monte Carlo ray tracing, using aggregated estimates of bias and variance to determine the pixel?s squared error distribution. This leads to a novel stopping criterion for denoised Monte Carlo image synthesis, that efficiently terminates rendering once a specified error is achieved.

References:


    [1]
    Attila T. ?fra. 2019. Intel? Open Image Denoise. https://www.openimagedenoise.org/.

    [2]
    Pontus Andersson, Jim Nilsson, Tomas Akenine-M?ller, Magnus Oskarsson, Kalle ?str?m, and Mark D. Fairchild. 2020. FLIP: A Difference Evaluator for Alternating Images. Proc. ACM Comput. Graph. Interact. Tech. 3, 2 (2020), 15?1. https://doi.org/10.1145/3406183

    [3]
    Jonghee Back, Binh-Son Hua, Toshiya Hachisuka, and Bochang Moon. 2022. Self-supervised post-correction for Monte Carlo denoising. In SIGGRAPH 2022 Conference Papers. ACM, 18:1?18:8. https://doi.org/10.1145/3528233.3530730

    [4]
    Jonghee Back, Binh-Son Hua, Toshiya Hachisuka, and Bochang Moon. 2023. Input-dependent uncorrelated weighting for Monte Carlo denoising. In SIGGRAPH Asia 2023 Conference Papers. ACM, 9:1?9:10. https://doi.org/10.1145/3610548.3618177

    [5]
    At?l?m G?ne? Baydin, Barak A. Pearlmutter, Alexey Andreyevich Radul, and Jeffrey Mark Siskind. 2018. Automatic differentiation in machine learning: a survey. Journal of Marchine Learning Research 18, 153 (2018), 1?43. http://jmlr.org/papers/v18/17-468.html

    [6]
    Pierre C Bellec and Cun-Hui Zhang. 2021. Second-order Stein: SURE for SURE and other applications in high-dimensional inference. The Annals of Statistics 49, 4 (2021), 1864?1903.

    [7]
    Benedikt Bitterli. 2016. Rendering Resources. https://benedikt-bitterli.me/resources/.

    [8]
    Mark R. Bolin and Gary W. Meyer. 1998. A perceptually based adaptive sampling algorithm. In SIGGRAPH ?98. 299?309. https://doi.org/10.1145/280814.280924

    [9]
    J?r?me Buisine, Andr? Bigand, R?mi Synave, Samuel Delepoulle, and Christophe Renaud. 2021a. Stopping criterion during rendering of computer-generated images based on SVD-entropy. Entropy 23, 1 (2021), 75. https://doi.org/10.3390/e23010075

    [10]
    J?r?me Buisine, Fabien Teytaud, Samuel Delepoulle, and Christophe Renaud. 2021b. Guided-generative network for noise detection in Monte-Carlo rendering. In International Conference on Machine Learning and Applications (ICMLA). IEEE, 61?66. https://doi.org/10.1109/ICMLA52953.2021.00018

    [11]
    Per H. Christensen and Wojciech Jarosz. 2016. The path to path-traced movies. Foundations and Trends in Computer Graphics and Vision 10, 2 (2016), 103?175. https://doi.org/10.1561/0600000073

    [12]
    Joseph Constantin, Ibtissam Constantin, Andre Bigand, and Denis Hamad. 2016. Perception of noise in global illumination based on inductive learning. In International Joint Conference on Neural Networks (IJCNN). IEEE, 5021?5028. https://doi.org/10.1109/IJCNN.2016.7727861

    [13]
    Holger Dammertz, Johannes Hanika, Alexander Keller, and Hendrik Lensch. 2010. A hierarchical automatic stopping condition for Monte Carlo global illumination. In Proceedings of the Winter School of Computer Graphics. 159?164.

    [14]
    Mark A. Z. Dipp? and Erling Henry Wold. 1985. Antialiasing through stochastic sampling. Computer Graphics (SIGGRAPH ?85) 19, 3 (July 1985), 69?78. https://doi.org/10.1145/325334.325182

    [15]
    Oskar Elek, Manu M. Thomas, and Angus Forbes. 2019. Learning patterns in sample distributions for Monte Carlo variance reduction. arXiv:1906.00124 [cs.GR]. https://doi.org/10.48550/arXiv.1906.00124

    [16]
    Arthur Firmino, Jeppe Revall Frisvad, and Henrik Wann Jensen. 2022. Progressive denoising of Monte Carlo rendered images. Computer Graphics Forum 41, 2 (May 2022), 1?11. https://doi.org/10.1111/cgf.14454

    [17]
    Arthur Firmino, Jeppe Revall Frisvad, and Henrik Wann Jensen. 2023. Denoising-aware adaptive sampling for Monte Carlo ray tracing. In SIGGRAPH 2023 Conference Proceedings. ACM, 32:1?32:11. https://doi.org/10.1145/3588432.3591537

    [18]
    Iliyan Georgiev, Jaroslav Krivanek, Toshiya Hachisuka, Derek Nowrouzezahrai, and Wojciech Jarosz. 2013. Joint importance sampling of low-order volumetric scattering. ACM Transactions on Graphics 32, 6 (2013), 164:1?164:14. https://doi.org/10.1145/2508363.2508411

    [19]
    Jeongmin Gu, Jose A. Iglesias-Guitian, and Bochang Moon. 2022. Neural James-Stein combiner for unbiased and biased renderings. ACM Transactions on Graphics 41, 6 (December 2022), 262:1?262:14. https://doi.org/10.1145/3550454.3555496

    [20]
    Baining Guo. 1998. Progressive radiance evaluation using directional coherence maps. In SIGGRAPH ?98. ACM, 255?266. https://doi.org/10.1145/280814.280888

    [21]
    Toshiya Hachisuka, Wojciech Jarosz, and Henrik Wann Jensen. 2010. A progressive error estimation framework for photon density estimation. ACM Transactions on Graphics 29, 6 (2010), 144:1?144:12. https://doi.org/10.1145/1882261.1866170

    [22]
    Wenzel Jakob, S?bastien Speierer, Nicolas Roussel, Merlin Nimier-David, Delio Vicini, Tizian Zeltner, Baptiste Nicolet, Miguel Crespo, Vincent Leroy, and Ziyi Zhang. 2022. Mitsuba 3 Renderer. https://mitsuba-renderer.org

    [23]
    James T. Kajiya. 1986. The rendering equation. Computer Graphics (SIGGRAPH ?86) 20, 4 (August 1986), 143?150. https://doi.org/10.1145/15922.15902

    [24]
    Nima Khademi Kalantari and Pradeep Sen. 2013. Removing the noise in Monte Carlo rendering with general image denoising algorithms. 32, 2pt1 (2013), 93?102. https://doi.org/10.1111/cgf.12029

    [25]
    Malvin H. Kalos. 1963. On the estimation of flux at a point by Monte Carlo. Nuclear science and engineering 16, 1 (1963), 111?117.

    [26]
    Alexander Keller, Luca Fascione, Marcos Fajardo, Iliyan Georgiev, Per Christensen, Johannes Hanika, Christian Eisenacher, and Gregory Nichols. 2015. The path tracing revolution in the movie industry. In SIGGRAPH 2015 Courses. ACM. https://doi.org/10.1145/2776880.2792699

    [27]
    Mark E. Lee, Richard A. Redner, and Samuel P. Uselton. 1985. Statistically optimized sampling for distributed ray tracing. Computer Graphics (SIGGRAPH ?85) 19, 3 (July 1985), 61?68. https://doi.org/10.1145/325334.325179

    [28]
    Tzu-Mao Li, Yu-Ting Wu, and Yung-Yu Chuang. 2012. SURE-based optimization for adaptive sampling and reconstruction. ACM Transactions on Graphics 31, 6 (November 2012), 194:1?194:9. https://doi.org/10.1145/2366145.2366213

    [29]
    Jun S Liu. 1994. Siegel?s formula via Stein?s identities. Statistics & Probability Letters 21, 3 (1994), 247?251. https://doi.org/10.1016/0167-7152(94)90121-X

    [30]
    Don P. Mitchell. 1987. Generating antialiased images at low sampling densities. Computer Graphics (SIGGRAPH ?87) 21, 4 (July 1987), 65?72. https://doi.org/10.1145/37401.37410

    [31]
    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. https://doi.org/10.1111/cgf.12004

    [32]
    Robb J. Muirhead. 2009. Aspects of multivariate statistical theory. John Wiley & Sons.

    [33]
    Karol Myszkowski. 2002. Perception-driven global illumination and rendering computation. In Advanced Computer Systems (ACS 2001). Springer, 267?288. https://doi.org/10.1007/978-1-4419-8530-9_22

    [34]
    Ryan S. Overbeck, Craig Donner, and Ravi Ramamoorthi. 2009. Adaptive wavelet rendering. ACM Transactions on Graphics 28, 5 (2009), 140:1?140:12. https://doi.org/10.1145/1618452.1618486

    [35]
    James Painter and Kenneth Sloan. 1989. Antialiased ray tracing by adaptive progressive refinement. Computer Graphics (SIGGRAPH ?89) 23, 3 (July 1989), 281?288. https://doi.org/10.1145/74333.74362

    [36]
    Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, Alban Desmaison, Andreas K?pf, Edward Yang, Zach DeVito, Martin Raison, Alykhan Tejani, Sasank Chilamkurthy, Benoit Steiner, Lu Fang, Junjie Bai, and Soumith Chintala. 2019. PyTorch: an imperative style, high-performance deep learning library. In Advances in Neural Information Processing Systems(NeurIPS 2019, Vol. 32).

    [37]
    Matt Pharr. 2018. Guest editor?s introduction: special issue on production rendering. ACM Transactions on Graphics 37, 3 (2018), 28:1?28:4. https://doi.org/10.1145/3212511

    [38]
    Werner Purgathofer. 1987. A statistical method for adaptive stochastic sampling. Computers & Graphics 11, 2 (1987), 157?162. https://doi.org/10.1016/0097-8493(87)90029-X

    [39]
    Sathish Ramani, Thierry Blu, and Michael Unser. 2008. Monte-Carlo SURE: a black-box optimization of regularization parameters for general denoising algorithms. IEEE Transactions on Image Processing 17, 9 (September 2008), 1540?1554. https://doi.org/10.1109/TIP.2008.2001404

    [40]
    Mahesh Ramasubramanian, Sumanta N. Pattanaik, and Donald P. Greenberg. 1999. A perceptually based physical error metric for realistic image synthesis. In SIGGRAPH ?99. ACM, 73?82. https://doi.org/10.1145/311535.311543

    [41]
    Jaume Rigau, Miquel Feixas, and Mateu Sbert. 2003a. Entropy-based adaptive sampling. In Graphics Interface (GI 2003). Canadian Human-Computer Communications Society and A K Peters, 149?158. https://doi.org/10.20380/GI2003.18

    [42]
    Jaume Rigau, Miquel Feixas, and Mateu Sbert. 2003b. Refinement criteria based on f-divergences. In Rendering Techniques (EGWR 2003). Eurographics Association, 260?269. https://doi.org/10.2312/EGWR/EGWR03/260-269

    [43]
    Fabrice Rousselle, Claude Knaus, and Matthias Zwicker. 2012. Adaptive rendering with non-local means filtering. ACM Transactions on Graphics 31, 6 (November 2012), 195:1?195:11. https://doi.org/10.1145/2366145.2366214

    [44]
    Fabrice Rousselle, Marco Manzi, and Matthias Zwicker. 2013. Robust denoising using feature and color information. Computer Graphics Forum 32, 7 (2013), 121?130. https://doi.org/10.1111/cgf.12219

    [45]
    Farnood Salehi, Marco Manzi, Gerhard Roethlin, Romann Weber, Christopher Schroers, and Marios Papas. 2022. Deep adaptive sampling and reconstruction using analytic distributions. ACM Transactions on Graphics 41, 6 (2022), 259:1?259:16. https://doi.org/10.1145/3550454.3555515

    [46]
    Charles M. Stein. 1981. Estimation of the mean of a multivariate normal distribution. The Annals of Statistics 9, 6 (November 1981), 1135?1151.

    [47]
    Nawel Takouachet, Samuel Delepoulle, Christophe Renaud, Nesrine Zoghlami, and Jo?o Manuel R. S. Tavares. 2017. Perception of noise and global illumination: toward an automatic stopping criterion based on SVM. Computers & Graphics 69 (2017), 49?58. https://doi.org/10.1016/j.cag.2017.09.008

    [48]
    Rasmus Tamstorf and Henrik Wann Jensen. 1997. Adaptive sampling and bias estimation in path tracing. In Rendering Techniques ?97 (EGWR). Springer, 285?295. https://doi.org/10.1007/978-3-7091-6858-5_26

    [49]
    Thijs Vogels, Fabrice Rousselle, Brian McWilliams, Gerhard R?thlin, Alex Harvill, David Adler, Mark Meyer, and Jan Nov?k. 2018. Denoising with kernel prediction and asymmetric loss functions. ACM Transactions on Graphics 37, 4 (August 2018), 124:1?124:15. https://doi.org/10.1145/3197517.3201388

    [50]
    Qing Xu, Mateu Sbert, Miquel Feixas, and Jizhou Sun. 2007. A new adaptive sampling technique for Monte Carlo global illumination. In Computer-Aided Design and Computer Graphics (CAD/Graphics). IEEE, 191?196. https://doi.org/10.1109/CADCG.2007.4407879

    [51]
    Qing Xu, Lianping Xing, Wei Wang, and Mateu Sbert. 2006. Adaptive sampling based on fuzzy inference. In GRAPHITE 2006. ACM, 311?317. https://doi.org/10.1145/1174429.1174482

    [52]
    Tobias Zirr, Johannes Hanika, and Carsten Dachsbacher. 2018. Re-weighting firefly samples for improved finite-sample Monte Carlo estimates. Computer Graphics Forum 37, 6 (2018), 410?421. https://doi.org/10.1111/cgf.13335


ACM Digital Library Publication:



Overview Page:



Submit a story:

If you would like to submit a story about this presentation, please contact us: historyarchives@siggraph.org