Fujia Su
Skip Abstract Section
Skip Supplemental Material SectionAbstract
Bidirectional path tracing (BDPT) can be accelerated by selecting appropriate light sub-paths for connection. However, existing algorithms need to perform frequent distribution reconstruction and have expensive overhead. We present a novel approach, SPCBPT, for probabilistic connections that constructs the light selection distribution in sub-path space. Our approach bins the sub-paths into multiple subspaces and keeps the sub-paths in the same subspace of low discrepancy, wherein the light sub-paths can be selected by a subspace-based two-stage sampling method, i.e., first sampling the light subspace and then resampling the light sub-paths within this subspace. The subspace-based distribution is free of reconstruction and provides efficient light selection at a very low cost. We also propose a method that considers the Multiple Importance Sampling (MIS) term in the light selection and thus obtain an MIS-aware distribution that can minimize the upper bound of variance of the combined estimator. Prior methods typically omit this MIS weights term. We evaluate our algorithm using various benchmarks, and the results show that our approach has superior performance and can significantly reduce the noise compared with the state-of-the-art method.
Supplemental Material
- B. Bitterli, C. Wyman, M. Pharr, P. Shirley, A. Lefohn, and W. Jarosz. 2020. Spatiotemporal reservoir resampling for real-time ray tracing with dynamic direct lighting. ACM Trans. Graph. (TOG) 39, 4 (07 2020), 148:1--17.Google Scholar
Digital Library
- C. R. A. Chaitanya, L. Belcour, T. Hachisuka, S. Premoze, J. Pantaleoni, and D. Nowrouzezahrai. 2018. Matrix Bidirectional Path Tracing. In Eurographics Symposium on Rendering - Experimental Ideas & Implementations. The Eurographics Association, 23--32.Google Scholar
- T. Davidovič, J. Krivanek, M. Hašan, and P. Slusallek. 2014. Progressive Light Transport Simulation on the GPU. ACM Trans. Graph. (TOG) 33, 3 (05 2014), 29:1--19.Google ScholarDigital Library
- X. Deng, S. Jiao, B. Bitterli, and W. Jarosz. 2019. Photon surfaces for robust, unbiased volumetric density estimation. ACM Trans. Graph. (TOG) 38, 4 (07 2019), 46:1--12.Google ScholarDigital Library
- S. Diolatzis, A. Gruson, W. Jakob, D. Nowrouzezahrai, and G. Drettakis. 2020. Practical Product Path Guiding Using Linearly Transformed Cosines. Computer Graphics Forum 39, 4 (07 2020), 23--33.Google Scholar
- R. Douc, A. Guillin, J. M. Marin, and C. P. Robert. 2007. Minimum variance importance sampling via Population Monte Carlo. ESAIM: Probability and Statistics 11 (2007), 427--447. Google ScholarCross Ref
- I. Georgiev, J. Krivanek, T. Davidovivc, and P. Slusallek. 2012a. Light Transport Simulation with Vertex Connection and Merging. ACM Trans. Graph. (TOG) 31, 6 (11 2012), 192:1--192:10.Google ScholarDigital Library
- I. Georgiev, J. Krivanek, S. Popov, and P. Slusallek. 2012b. Importance Caching for Complex Illumination. Computer Graphics Forum 31, 2 (05 2012), 701--710.Google Scholar
- P. Grittmann, I. Georgiev, and P. Slusallek. 2021. Correlation-Aware Multiple Importance Sampling for Bidirectional Rendering Algorithms. Computer Graphics Forum 40, 2 (05 2021), 231--238.Google Scholar
- J. Guo, P. Bauszat, J. Bikker, and E. Eisemann. 2018. Primary sample space path guiding. In Eurographics Symposium on Rendering, Vol. 2018. The Eurographics Association, 73--82.Google Scholar
- T. Hachisuka and H. W. Jensen. 2009. Stochastic Progressive Photon Mapping. ACM Trans. Graph. (TOG) 28, 5 (12 2009), 141:1--8.Google ScholarDigital Library
- T. Hachisuka, J. Pantaleoni, and H. W. Jensen. 2012. A Path Space Extension for Robust Light Transport Simulation. ACM Trans. Graph. (TOG) 31, 6 (11 2012), 191:1--10.Google ScholarDigital Library
- M. Hašan and F. Pellacini. 2007. Matrix Row-Column Sampling for the Many-Light Problem. ACM Trans. Graph. (TOG) 26, 3 (08 2007), 26:1--10.Google ScholarDigital Library
- S. Herholz, O. Elek, J. Vorba, H. Lensch, and J. Krivanek. 2016. Product Importance Sampling for Light Transport Path Guiding. Computer Graphics Forum 35, 4 (06 2016), 67--77.Google Scholar
- W. Jakob and S. Marschner. 2012. Manifold Exploration: A Markov Chain Monte Carlo Technique for Rendering Scenes with Difficult Specular Transport. ACM Trans. Graph. (TOG) 31, 4 (07 2012), 58:1--13.Google ScholarDigital Library
- H. w. Jensen. 1996. Importance Driven Path Tracing Using the Photon Map. Eurographics Rendering Workshop (09 1996), 326--335.Google Scholar
- A. Keller. 1997. Instant radiosity. In Proceedings of the 24th annual conference on Computer graphics and interactive techniques. 49--56.Google ScholarDigital Library
- D. Kingma and J. Ba. 2014. Adam: A Method for Stochastic Optimization. International Conference on Learning Representations (12 2014).Google Scholar
- J. Krivanek, M. Hasan, A. Arbree, C. Dachsbacher, A. Keller, and B. Walter. 2014. Scalable Realistic Rendering with Many-Light Methods. Computer Graphics Forum 33, 1 (02 2014), 88--104.Google Scholar
- E. P. Lafortune and Y. D. Willems. 1993. Bi-Directional Path Tracing. In Proceedings of Compugraphics. 145--153.Google Scholar
- E. P. Lafortune and Y. D. Willems. 1999. A 5D Tree to Reduce the Variance of Monte Carlo Ray Tracing. In Rendering Techniques.Google Scholar
- Z. Lin, S. Li, X. Zeng, C. Zhang, J. Jia, G. Wang, and D. Manocha. 2020. CPPM: chi-squared progressive photon mapping. ACM Trans. Graph. (TOG) 39, 6 (11 2020), 240:1--12.Google ScholarDigital Library
- T. Müller, B. Mcwilliams, F. Rousselle, M. Gross, and J. Novák. 2019. Neural Importance Sampling. ACM Trans. Graph. (TOG) 38, 5 (10 2019), 145:1--19.Google ScholarDigital Library
- T. Müller, F. Rousselle, A. Keller, and J. Novák. 2020. Neural Control Variates. ACM Trans. Graph. (TOG) 39, 6 (11 2020), 243:1--19.Google ScholarDigital Library
- T. Müller, M. Gross, and J. Novák. 2017. Practical Path Guiding for Efficient LightTransport Simulation. Computer Graphics Forum 36, 4 (07 2017), 91--100.Google Scholar
- K. Nabata, K. Iwasaki, and Y. Dobashi. 2020a. Resampling-aware Weighting Functions for Bidirectional Path Tracing Using Multiple Light Sub-Paths. ACM Trans. Graph. (TOG) 39, 2 (03 2020), 15:1--11.Google ScholarDigital Library
- K. Nabata, K. Iwasaki, and Y. Dobashi. 2020b. Two-stage Resampling for Bidirectional Path Tracing with Multiple Light Sub-paths. Computer Graphics Forum 39, 7 (10 2020), 219--230.Google Scholar
- J. Ou and F. Pellacini. 2011. LightSlice: matrix slice sampling for the many-lights problem. ACM Trans. Graph. (TOG) 30, 6 (12 2011), 179:1--8.Google ScholarDigital Library
- A. Pajot, L. Barthe, M. Paulin, and P. Poulin. 2011. Combinatorial bidirectional path-tracing for efficient hybrid CPU/GPU rendering. Computer Graphics Forum 30, 2 (2011), 315--324.Google ScholarCross Ref
- S. G. Parker, J. Bigler, A. Dietrich, H. Friedrich, J. Hoberock, D. Luebke, D. McAllister, M. McGuire, K. Morley, A. Robison, et al. 2010. Optix: a general purpose ray tracing engine. ACM Trans. Graph. (TOG) 29, 4 (07 2010), 66:1--13.Google ScholarDigital Library
- S. Popov, R. Ramamoorthi, F. Durand, and G. Drettakis. 2015. Probabilistic Connections for Bidirectional Path Tracing. Computer Graphics Forum 34, 4 (07 2015), 75--86.Google Scholar
- A. Rath, P. Grittmann, Sebastian H., P. Vévoda, P. Slusallek, and J. Křivánek. 2020. Variance-Aware Path Guiding. ACM Trans. Graph. (TOG) 39, 4 (07 2020), 151:1--12.Google ScholarDigital Library
- M. Sbert, V. Havran, and L. Szirmay-Kalos. 2016. Variance Analysis of Multi-sample and One-sample Multiple Importance Sampling. Computer Graphics Forum 35, 7 (10 2016), 451--460.Google Scholar
- J. Talbot, D. Cline, and P. Egbert. 2005. Importance Resampling for Global Illumination. Eurographics Symposium on Rendering, 139--146.Google Scholar
- Y. Tokuyoshi and T. Harada. 2019. Hierarchical russian roulette for vertex connections. ACM Trans. Graph. (TOG) 38, 4 (07 2019), 36:1--12.Google ScholarDigital Library
- D. V. Antwerpen. 2011. Recursive MIS Computation for Streaming BDPT on the GPU. Technical Report.Google Scholar
- E. Veach and L. Guibas. 1995a. Bidirectional estimators for light transport. In Photorealistic Rendering Techniques. 145--167.Google Scholar
- E. Veach and L. Guibas. 1995b. Optimally Combining Sampling Techniques for Monte Carlo Rendering. In Proceedings of the 22nd Annual Conference on Computer Graphics and Interactive Techniques. 419--428.Google Scholar
- E. Veach and L. J. Guibas. 1997. Metropolis light transport. In Proceedings of the 24th annual conference on Computer graphics and interactive techniques. 65--76.Google Scholar
- P. Vévoda, I. Kondapaneni, and J. Křivánek. 2018. Bayesian Online Regression for Adaptive Direct Illumination Sampling. ACM Trans. Graph. (TOG) 37, 4 (07 2018), 125:1--12.Google ScholarDigital Library
- J. Vorba, J. Hanika, S. Herholz, T. Müller, J. Křivánek, and A. Keller. 2019. Path Guiding in Production. In ACM SIGGRAPH 2019 Courses. 18:41--45.Google Scholar
- J. Vorba, O. Karlík, M. Šik, T. Ritschel, and J. Krivanek. 2014. On-line Learning of Parametric Mixture Models for Light Transport Simulation. ACM Trans. Graph. (TOG) 33, 4 (07 2014), 101:1--11.Google ScholarDigital Library
- B. Walter, A. Arbree, K. Bala, and D. Greenberg. 2006. Multidimensional Lightcuts. ACM Trans. Graph. (TOG) 25 (07 2006), 1081--1088.Google Scholar
- B. Walter, S. Fernandez, A. Arbree, K. Bala, M. Donikian, and D. Greenberg. 2005. Lightcuts: a scalable approach to illumination. ACM Trans. Graph. (TOG) 24, 3 (07 2005), 1098--1107.Google ScholarDigital Library
- B. Walter, P. Khungurn, and K. Bala. 2012. Bidirectional lightcuts. ACM Trans. Graph. (TOG) 31, 4 (07 2012), 59:1--11.Google ScholarDigital Library
- Y. Wang, Y. Wu, T. Li, and Y. Chuang. 2021. Learning to Cluster for Rendering with Many Lights. ACM Trans. Graph. (TOG) 40, 6 (12 2021), 277:1--10.Google ScholarDigital Library
- Y. Wu and Y. Chuang. 2013. VisibilityCluster: Average Directional Visibility for Many-Light Rendering. IEEE transactions on visualization and computer graphics 19 (09 2013), 1566--1578.Google Scholar
Index Terms
SPCBPT: subspace-based probabilistic connections for bidirectional path tracing
Recommendations
Resampling-aware Weighting Functions for Bidirectional Path Tracing Using Multiple Light Sub-Paths
Bidirectional path tracing (BPT) with multiple importance sampling (MIS) is a popular technique for rendering realistic images. Recently, it has been shown that BPT can be improved by preparing multiple light sub-paths and by resampling a small number ...
Joint importance sampling of low-order volumetric scattering
Central to all Monte Carlo-based rendering algorithms is the construction of light transport paths from the light sources to the eye. Existing rendering approaches sample path vertices incrementally when constructing these light transport paths. The ...
Feature extraction using constrained maximum variance mapping
In this paper, an efficient feature extraction method named as constrained maximum variance mapping (CMVM) is developed. The proposed algorithm can be viewed as a linear approximation of multi-manifolds learning based approach, which takes the local ...
Comments