Abstract
Monte Carlo ray tracing is considered one of the most effective techniques for rendering photo-realistic imagery, but requires a large number of ray samples to produce converged or even visually pleasing images. We develop a novel image-plane adaptive sampling and reconstruction method based on local regression theory. A novel local space estimation process is proposed for employing the local regression, by robustly addressing noisy high-dimensional features. Given the local regression on estimated local space, we provide a novel two-step optimization process for selecting bandwidths of features locally in a data-driven way. Local weighted regression is then applied using the computed bandwidths to produce a smooth image reconstruction with well-preserved details. We derive an error analysis to guide our adaptive sampling process at the local space. We demonstrate that our method produces more accurate and visually pleasing results over the state-of-the-art techniques across a wide range of rendering effects. Our method also allows users to employ an arbitrary set of features, including noisy features, and robustly computes a subset of them by ignoring noisy features and decorrelating them for higher quality.
Supplemental Material
Available for Download
Supplemental movie, appendix, image and software files for, Adaptive Rendering Based on Weighted Local Regression
- P. Bauszat, M. Eisemann, and M. Magnor. 2011. Guided image filtering for interactive high-quality global illumination. Comput. Graph. Forum 30, 4, 1361--1368. Google ScholarDigital Library
- L. Belcour, C. Soler, K. Subr, N. Holzschuch, and F. Durand. 2013. 5D covariance tracing for efficient defocus and motion blur. ACM Trans. Graph. 32, 3, 31:1--31:18. Google ScholarDigital Library
- W. S. Cleveland and C. L. Loader. 1996. Smoothing by local regression: Principles and methods. In Statistical Theory and Computational Aspects of Smoothing, Springer, New York, 10--49.Google Scholar
- H. Dammertz, D. Sewtz, J. Hanika, and H. P. A. Lensch. 2010. Edge-avoiding a-trous wavelet transform for fast global illumination filtering. In Proceedings of the Conference on High Performance Graphics. 67--75. Google ScholarDigital Library
- C. Decoro, T. Weyrich, and S. Rusinkiewicz. 2010. Density based outlier rejection in monte carlo rendering. Comput. Graph. Forum 29, 7, 2119--2125.Google ScholarCross Ref
- K. Egan, F. Durand, and R. Ramamoorthi. 2011a. Practical filtering for efficient ray-traced directional occlusion. ACM Trans. Graph. 30, 6, 180:1--180:10. Google ScholarDigital Library
- K. Egan, F. Hecht, F. Durand, and R. Ramamoorthi. 2011b. Frequency analysis and sheared filtering for shadow light fields of complex occluders. ACM Trans. Graph. 20, 2, 9:1--9:13. Google ScholarDigital Library
- K. Egan, Y.-T. Tseng, N. Holzschuch, F. Durand, and R. Ramamoorthi. 2009. Frequency analysis and sheared reconstruction for rendering motion blur. ACM Trans. Graph. 28, 3, 93:1--93:13. Google ScholarDigital Library
- T. Hachisuka, W. Jarosz, and H. W. Jensen. 2010. A progressive error estimation framework for photon density estimation. ACM Trans. Graph. 29, 6, 144:1--144:12. Google ScholarDigital Library
- T. Hachisuka, W. Jarosz, R. P. Weistroffer, K. Dale, G. Humphreys, M. Zwicker, and H. W. Jensen. 2008. Multidimensional adaptive sampling and reconstruction for ray tracing. In Proceedings of the Annual ACM SIGGRAPH Conference on Computer Graphics and Interactive Techniques. 33:1--33:10. Google ScholarDigital Library
- P. Hansen. 1987. The truncated SVD as a method for regularization. BIT Numer. Math. 27, 4, 534--553. Google ScholarDigital Library
- K. He, J. Sun, and X. Tang. 2013. Guided image filtering. IEEE Trans. Pattern Anal. Mach. Intell. 35, 6, 1397--1409. Google ScholarDigital Library
- N. K. Kalantri and P. Sen. 2013. Removing the noise in Monte Carlo rendering with general image denoising algorithms. Comput. Graph. Forum 32, 2, 93--102.Google ScholarCross Ref
- A. S. Kaplanyan and C. Dachsbacher. 2013. Adaptive progressive photon mapping. ACM Trans. Graph. 32, 2, 16:1--16:13. Google ScholarDigital Library
- J. Lehtinen, T. Aila, J. Chen, S. Laine, and F. Durand. 2011. Temporal light field reconstruction for rendering distribution effects. ACM Trans. Graph. 30, 4, 55:1--55:12. Google ScholarDigital Library
- J. Lehtinen, T. Aila, S. Laine, and F. Durand. 2012. Reconstructing the indirect light field for global illumination. ACM Trans. Graph. 31, 4, 51:1--51:10. Google ScholarDigital Library
- T.-M. Li, Y.-T. Wu, and Y.-Y. Chuang. 2012. Sure-based optimization for adaptive sampling and reconstruction. ACM Trans. Graph. 31, 6, 194:1--194:9. Google ScholarDigital Library
- M. D. McCool. 1999. Anisotropic diffusion for Monte Carlo noise reduction. ACM Trans. Graph. 18, 2, 171--194. Google ScholarDigital Library
- M. Meyer and J. Anderson. 2006. Statistical acceleration for animated global illumination. ACM Trans. Graph. 25, 3, 1075--1080. Google ScholarDigital Library
- D. P. Mitchell. 1987. Generating antialiased images at low sampling densities. In Proceedings of the Annual ACM SIGGRAPH Conference on Computer Graphics and Interactive Techniques. Vol. 21, 65--72. Google ScholarDigital Library
- B. Moon, J. Y. Jun, J. Lee, K. Kim, T. Hachisuka, and S.-E. Yoon. 2013. Robust image denoising using a virtual flash image for Monte Carlo ray tracing. Comput. Graph. Forum 32, 1, 139--151.Google ScholarCross Ref
- J. C. Nash. 1975. A one-sided transformation method for the singular value decomposition and algebraic eigenproblem. The Comput. J. 18, 1, 74--76.Google ScholarCross Ref
- R. S. Overbeck, C. Donner, and R. Ramamoorthi. 2009. Adaptive wavelet rendering. In Proceedings of the Annual ACM SIGGRAPH Conference on Computer Graphics and Interactive Techniques in Asia. 140:1--140:12. Google ScholarDigital Library
- M. Pharr and G. Humphreys. 2010. Physically Based Rendering: From Theory to Implementation 2nd Ed. Morgan Kaufmann, San Fransisco. Google ScholarDigital Library
- T. Ritschel, T. Engelhardt, T. Grosch, H.-P. Seidel, J. Kautz, and C. Dachsbacher. 2009. Micro-rendering for scalable, parallel final gathering. In Proceedings of the Annual ACM SIGGRAPH Conference on Computer Graphics and Interactive Techniques in Asia. 1--8. Google ScholarDigital Library
- F. Rousselle, C. Knaus, and M. Zwicker. 2011. Adaptive sampling and reconstruction using greedy error minimization. In Proceedings of the Annual ACM SIGGRAPH Conference on Computer Graphics and Interactive Techniques in Asia. 159:1--159:12. Google ScholarDigital Library
- F. Rousselle, C. Knaus, and M. Zwicker. 2012. Adaptive rendering with non-local means filtering. ACM Trans. Graph. 31, 6, 195:1--195:11. Google ScholarDigital Library
- D. Ruppert and M. Wand. 1994. Multivariate locally weighted least squares regression. The Ann. Statist. 22, 3, 1346--1370.Google ScholarCross Ref
- H. E. Rushmeier and G. J. Ward. 1994. Energy preserving non-linear filters. In Proceedings of the Annual ACM SIGGRAPH Conference on Computer Graphics and Interactive Techniques. 131--138. Google ScholarDigital Library
- J. Schwarzhaupt, H. W. Jensen, and W. Jarosz. 2012. Practical Hessian-based error control for irradiance caching. ACM Trans. Graph. 31, 6, 193:1--193:10. Google ScholarDigital Library
- B. Segovia, J. C. Iehl, R. Mitanchey, and B. Peroche. 2006. Non-interleaved deferred shading of interleaved sample patterns. In Proceedings of the 21st ACM SIGGRAPH/Eurographics Symposium on Graphics Hardware. 53--60. Google ScholarDigital Library
- P. Sen and S. Darabi. 2012. On filtering the noise from the random parameters in Monte Carlo rendering. ACM Trans. Graph. 31, 3, 18:1--18:15. Google ScholarDigital Library
- P. Shirley, T. Aila, J. Cohen, E. Enderton, S. Laine, D. Luebke, and M. McGuire. 2011. A local image reconstruction algorithm for stochastic rendering. In Proceedings of the Symposium on Interactive 3D Graphics and Games. 9--14. Google ScholarDigital Library
- C. Soler, K. Subr, F. Durand, N. Holzschuch, and F. Sillion. 2009. Fourier depth of field. ACM Trans. Graph. 28, 2, 18:1--18:12. Google ScholarDigital Library
- G. Stewart. 1993. On the early history of the singular value decomposition. SIAM Rev. 35, 4, 551--566. Google ScholarDigital Library
Index Terms
- Adaptive Rendering Based on Weighted Local Regression
Recommendations
Adaptive polynomial rendering
In this paper, we propose a new adaptive rendering method to improve the performance of Monte Carlo ray tracing, by reducing noise contained in rendered images while preserving high-frequency edges. Our method locally approximates an image with ...
Adaptive rendering based on a weighted mixed-order estimator
In this paper, we propose a novel adaptive rendering method to robustly handle noise artifacts and outliers of Monte Carlo ray tracing by combining the Nadaraya---Watson and robust local linear estimators while efficiently preserving fine details. Our ...
Adaptive rendering with linear predictions
We propose a new adaptive rendering algorithm that enhances the performance of Monte Carlo ray tracing by reducing the noise, i.e., variance, while preserving a variety of high-frequency edges in rendered images through a novel prediction based ...
Comments