Abstract
Physically based differentiable rendering algorithms propagate derivatives through realistic light transport simulations and have applications in diverse areas including inverse reconstruction and machine learning. Recent progress has led to unbiased methods that can simultaneously compute derivatives with respect to millions of parameters. At the same time, elementary properties of these methods remain poorly understood.
Current algorithms for differentiable rendering are constructed by mechanically differentiating a given primal algorithm. While convenient, such an approach is simplistic because it leaves no room for improvement. Differentiation produces major changes in the integrals that occur throughout the rendering process, which indicates that the primal and differential algorithms should be decoupled so that the latter can suitably adapt.
This leads to a large space of possibilities: consider that even the most basic Monte Carlo path tracer already involves several design choices concerning the techniques for sampling materials and emitters, and their combination, e.g. via multiple importance sampling (MIS). Differentiation causes a veritable explosion of this decision tree: should we differentiate only the estimator, or also the sampling technique? Should MIS be applied before or after differentiation? Are specialized derivative sampling strategies of any use? How should visibility-related discontinuities be handled when millions of parameters are differentiated simultaneously? In this paper, we provide a taxonomy and analysis of different estimators for differential light transport to provide intuition about these and related questions.
Supplemental Material
- Dejan Azinović, Tzu-Mao Li, Anton Kaplanyan, and Matthias Nießner. 2019. Inverse Path Tracing for Joint Material and Lighting Estimation. In Proceedings of Computer Vision and Pattern Recognition (CVPR), IEEE.Google Scholar
Cross Ref
- Sai Bangaru, Tzu-Mao Li, and Frédo Durand. 2020. Unbiased Warped-Area Sampling for Differentiable Rendering. ACM Transactions on Graphics 39, 6 (2020), 245:1--245:18.Google Scholar
Digital Library
- Petr Beckmann and Andre Spizzichino. 1987. The scattering of electromagnetic waves from rough surfaces. Norwood (1987).Google Scholar
- Laurent Belcour, Cyril Soler, Kartic Subr, Nicolas Holzschuch, and Fredo Durand. 2013. 5D Covariance Tracing for Efficient Defocus and Motion Blur. ACM Transactions on Graphics 32, 3 (July 2013). Google Scholar
Digital Library
- Benedikt Bitterli. 2016. Rendering resources. https://benedikt-bitterli.me/resources/.Google Scholar
- Chengqian Che, Fujun Luan, Shuang Zhao, Kavita Bala, and Ioannis Gkioulekas. 2018. Inverse Transport Networks. arXiv preprint arXiv:1809.10820 (2018).Google Scholar
- Min Chen and James Arvo. 2000. Theory and Application of Specular Path Perturbation. ACM Transactions on Graphics 19, 4 (Oct. 2000), 246--278.Google Scholar
Digital Library
- Robert L Cook and Kenneth E. Torrance. 1982. A reflectance model for computer graphics. ACM Transactions on Graphics (ToG) 1, 1 (1982), 7--24.Google Scholar
Digital Library
- Luc Devroye. 1986. Non-Uniform Random Variate Generation. Springer-Verlag.Google Scholar
- Ioannis Gkioulekas, Anat Levin, and Todd Zickler. 2016. An evaluation of computational imaging techniques for heterogeneous inverse scattering. In European Conference on Computer Vision. Springer, 685--701.Google Scholar
Cross Ref
- Ioannis Gkioulekas, Shuang Zhao, Kavita Bala, Todd Zickler, and Anat Levin. 2013. Inverse Volume Rendering with Material Dictionaries. ACM Transactions on Graphics 32, 6, Article 162 (Nov. 2013).Google Scholar
Digital Library
- Andreas Griewank and Andrea Walther. 2008. Evaluating derivatives: principles and techniques of algorithmic differentiation. Vol. 105. SIAM.Google Scholar
- Carole K. Hayakawa, Jerome Spanier, Frédéric Bevilacqua, Andrew K. Dunn, Joon S. You, Bruce J. Tromberg, and Vasan Venugopalan. 2001. Perturbation Monte Carlo methods to solve inverse photon migration problems in heterogeneous tissues. Opt. Lett. 26, 17 (Sep 2001), 1335--1337.Google Scholar
Cross Ref
- Paul S Heckbert. 1989. Fundamentals of texture mapping and image warping. Master's thesis.Google Scholar
- Eric Heitz and Eugene D'Eon. 2014. Importance Sampling Microfacet-Based BSDFs using the Distribution of Visible Normals. Computer Graphics Forum 33, 4 (July 2014), 103--112. Google Scholar
Digital Library
- Binh-Son Hua, Adrien Gruson, Victor Petitjean, Matthias Zwicker, Derek Nowrouzezahrai, Elmar Eisemann, and Toshiya Hachisuka. 2019. A Survey on Gradient-Domain Rendering. Computer Graphics Forum 38, 2 (2019), 455--472.Google Scholar
Cross Ref
- Homan Igehy. 1999. Tracing Ray Differentials. In Proceedings of the 26th Annual Conference on Computer Graphics and Interactive Techniques (SIGGRAPH 99). 179--186. Google Scholar
Digital Library
- 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 31, 4 (July 2012).Google Scholar
Digital Library
- Hiroharu Kato, Yoshitaka Ushiku, and Tatsuya Harada. 2018. Neural 3D Mesh Renderer. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR).Google Scholar
Cross Ref
- Jaroslav Krivánek, Pascal Gautron, Sumanta Pattanaik, and Kadi Bouatouch. 2005. Radiance caching for efficient global illumination computation. IEEE Transactions on Visualization and Computer Graphics 11, 5 (2005), 550--561.Google Scholar
Digital Library
- Samuli Laine, Janne Hellsten, Tero Karras, Yeongho Seol, Jaakko Lehtinen, and Timo Aila. 2020. Modular Primitives for High-Performance Differentiable Rendering. ACM Transactions on Graphics 39, 6 (2020).Google Scholar
Digital Library
- Tzu-Mao Li, Miika Aittala, Frédo Durand, and Jaakko Lehtinen. 2018. Differentiable Monte Carlo Ray Tracing through Edge Sampling. ACM Transactions on Graphics (Proc. SIGGRAPH Asia) 37, 6 (2018), 222:1--222:11.Google Scholar
- Shichen Liu, Weikai Chen, Tianye Li, and Hao Li. 2019. Soft Rasterizer: Differentiable Rendering for Unsupervised Single-View Mesh Reconstruction. CoRR abs/1901.05567 (2019). arXiv:1901.05567 http://arxiv.org/abs/1901.05567Google Scholar
- Matthew M Loper and Michael J Black. 2014. OpenDR: An approximate differentiable renderer. In European Conference on Computer Vision. Springer.Google Scholar
Cross Ref
- Guillaume Loubet, Nicolas Holzschuch, and Wenzel Jakob. 2019. Reparameterizing discontinuous integrands for differentiable rendering. Transactions on Graphics (Proceedings of SIGGRAPH Asia) 38, 6 (Dec. 2019).Google Scholar
Digital Library
- Iván Lux and Lázló Koblinger. 1990. Monte Carlo Particle Transport Methods: Neutron and Photon Calculations. CRC Press, Boston.Google Scholar
- Don Mitchell and Pat Hanrahan. 1992. Illumination from curved reflectors. In Proceedings of the 19th annual conference on Computer graphics and interactive techniques. 283--291.Google Scholar
Digital Library
- Merlin Nimier-David, Sébastien Speierer, Benoît Ruiz, and Wenzel Jakob. 2020. Radiative Backpropagation: An Adjoint Method for Lightning-Fast Differentiable Rendering. Transactions on Graphics (Proceedings of SIGGRAPH) 39, 4 (July 2020).Google Scholar
Digital Library
- Merlin Nimier-David, Delio Vicini, Tizian Zeltner, and Wenzel Jakob. 2019. Mitsuba 2: A Retargetable Forward and Inverse Renderer. Transactions on Graphics (Proceedings of SIGGRAPH Asia) 38, 6 (Dec. 2019).Google Scholar
Digital Library
- Art B. Owen. 2013. Monte Carlo theory, methods and examples. https://statweb.stanford.edu/~owen/mc/Google Scholar
- Steven G. Parker, James Bigler, Andreas Dietrich, Heiko Friedrich, Jared Hoberock, David Luebke, David McAllister, Morgan McGuire, Keith Morley, Austin Robison, and Martin Stich. 2010. OptiX: A General Purpose Ray Tracing Engine. ACM Transactions on Graphics 29, 4, Article 66 (July 2010), 13 pages. Google Scholar
Digital Library
- Felix Petersen, Amit H. Bermano, Oliver Deussen, and Daniel Cohen-Or. 2019. Pix2Vex: Image-to-Geometry Reconstruction using a Smooth Differentiable Renderer. CoRR abs/1903.11149 (2019). arXiv:1903.11149 http://arxiv.org/abs/1903.11149Google Scholar
- Matt Pharr, Wenzel Jakob, and Greg Humphreys. 2016. Physically Based Rendering: From Theory to Implementation (3rd ed.) (3rd ed.). Morgan Kaufmann Publishers Inc., San Francisco, CA, USA. 1266 pages.Google Scholar
Digital Library
- Ravi Ramamoorthi, Dhruv Mahajan, and Peter Belhumeur. 2007. A first-order analysis of lighting, shading, and shadows. ACM Transactions on Graphics (TOG) 26, 1 (2007).Google Scholar
Digital Library
- Helge Rhodin, Nadia Robertini, Christian Richardt, Hans-Peter Seidel, and Christian Theobalt. 2015. A Versatile Scene Model with Differentiable Visibility Applied to Generative Pose Estimation. In Proceedings of ICCV 2015.Google Scholar
Digital Library
- Kenneth E Torrance and Ephraim M Sparrow. 1967. Theory for off-specular reflection from roughened surfaces. Josa 57, 9 (1967), 1105--1114.Google Scholar
Cross Ref
- T. S. Trowbridge and K. P. Reitz. 1975. J. Opt. Soc. Am. 65, 5 (May 1975), 531--536.Google Scholar
Cross Ref
- Eric Veach and Leonidas J. Guibas. 1995. Optimally Combining Sampling Techniques for Monte Carlo Rendering. In Proceedings of the 22nd Annual Conference on Computer Graphics and Interactive Techniques (SIGGRAPH '95). Association for Computing Machinery, New York, NY, USA, 419--428. Google Scholar
Digital Library
- Darko Veberic. 2010. Having Fun with Lambert W(x) Function. CoRR abs/1003.1628 (2010). arXiv:1003.1628 http://arxiv.org/abs/1003.1628Google Scholar
- Delio Vicini, Sébastien Speierer, and Wenzel Jakob. 2021. Path Replay Backpropagation: Differentiating Light Paths using Constant Memory and Linear Time. Transactions on Graphics (Proceedings of SIGGRAPH) 40, 4 (Aug. 2021). Google Scholar
Digital Library
- Bruce Walter, Stephen R. Marschner, Hongsong Li, and Kenneth E. Torrance. 2007. Microfacet Models for Refraction through Rough Surfaces. In Proceedings of the 18th Eurographics Conference on Rendering Techniques (Grenoble, France) (EGSR'07). Eurographics Association, Goslar, DEU, 195--206.Google Scholar
- G J Ward and P S Heckbert. 1992. Irradiance gradients. Technical Report. LawrenceGoogle Scholar
- Berkeley Lab., CA (United States); Ecole Polytechnique Federale, Lausanne (Switzerland); Technische Hogeschool Delft (Netherlands). Dept. of Technical Mathematics and Informatics.Google Scholar
- Tizian Zeltner, Iliyan Georgiev, and Wenzel Jakob. 2020. Specular Manifold Sampling for Rendering High-Frequency Caustics and Glints. Transactions on Graphics (Proceedings of SIGGRAPH) 39, 4 (July 2020). Google Scholar
Digital Library
- Cheng Zhang, Bailey Miller, Kai Yan, Ioannis Gkioulekas, and Shuang Zhao. 2020. Path-Space Differentiable Rendering. ACM Transactions on Graphics 39, 4 (2020), 143:1--143:19.Google Scholar
Digital Library
- Cheng Zhang, Lifan Wu, Changxi Zheng, Ioannis Gkioulekas, Ravi Ramamoorthi, and Shuang Zhao. 2019. A Differential Theory of Radiative Transfer. ACM Transactions on Graphics 38, 6 (2019), 227:1--227:16.Google Scholar
Digital Library
- Shaung Zhao, Lifan Wu, Frédo Durand, and Ravi Ramamoorthi. 2016. Downsampling Scattering Parameters for Rendering Anisotropic Media. ACM Transactions on Graphics 35, 6 (2016).Google Scholar
Digital Library
Index Terms
Monte Carlo estimators for differential light transport
Recommendations
Unbiased warped-area sampling for differentiable rendering
Differentiable rendering computes derivatives of the light transport equation with respect to arbitrary 3D scene parameters, and enables various applications in inverse rendering and machine learning. We present an unbiased and efficient differentiable ...
Antithetic sampling for Monte Carlo differentiable rendering
Stochastic sampling of light transport paths is key to Monte Carlo forward rendering, and previous studies have led to mature techniques capable of drawing high-contribution light paths in complex scenes. These sampling techniques have also been applied ...
Unbiased inverse volume rendering with differential trackers
Volumetric representations are popular in inverse rendering because they have a simple parameterization, are smoothly varying, and transparently handle topology changes. However, incorporating the full volumetric transport of light is costly and ...





Comments