請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/81287完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 莊永裕(Yung-Yu Chuang) | |
| dc.contributor.author | Yu-Chen Wang | en |
| dc.contributor.author | 王宇辰 | zh_TW |
| dc.date.accessioned | 2022-11-24T03:40:55Z | - |
| dc.date.available | 2021-08-06 | |
| dc.date.available | 2022-11-24T03:40:55Z | - |
| dc.date.copyright | 2021-08-06 | |
| dc.date.issued | 2021 | |
| dc.date.submitted | 2021-07-26 | |
| dc.identifier.citation | [1] B. Bitterli, C. Wyman, M. Pharr, P. Shirley, A. Lefohn, and W. Jarosz. Spatiotemporal reservoir resampling for realtime ray tracing with dynamic direct lighting. ACM Trans. Graph. (Proc. SIGGRAPH), 39(4):148–1, 2020. [2] L. Bottou, F. E. Curtis, and J. Nocedal. Optimization methods for largescale machine learning. Siam Review, 60(2):223–311, 2018. [3] C. Dachsbacher, J. Křivánek, M. Hašan, A. Arbree, B. Walter, and J. Novák. Scalable realistic rendering with manylight methods. Computer Graphics Forum, 33(1):88–104, 2014. [4] C. Dachsbacher and M. Stamminger. Reflective shadow maps. In Proceedings of the 2005 symposium on Interactive 3D graphics and games, pages 203–231, 2005. [5] K. Dahm and A. Keller. Learning light transport the reinforced way. In ACM SIGGRAPH 2017 Talks. Association for Computing Machinery, 2017. [6] T. Davidovič, J. Křivánek, M. Hašan, P. Slusallek, and K. Bala. Combining global and local virtual lights for detailed glossy illumination. ACM Trans. Graph. (Proc. SIGGRAPH Asia), 29(6):1–8, 2010. [7] M. Donikian, B. Walter, K. Bala, S. Fernandez, and D. P. Greenberg. Accurate direct illumination using iterative adaptive sampling. IEEE Trans. on Visualization and Computer Graphics, 12(3):353–364, 2006. [8] F. Durand, G. Drettakis, and C. Puech. The visibility skeleton: A powerful and efficient multipurpose global visibility tool. In Proceedings of the 24th annual conference on Computer graphics and interactive techniques, pages 89–100, 1997. [9] A. C. Estevez and C. Kulla. Importance sampling of many lights with adaptive tree splitting. ACM Comput. Graph. Interact. Tech. (Proc. HPG), 1(2):25:1–25:17, 2018. [10] S. Fernandez, K. Bala, and D. P. Greenberg. Local illumination environments for direct lighting acceleration. In Proceedings of the 13th Eurographics Workshop on Rendering, page 7–14. Eurographics Association, 2002. [11] I. Georgiev, J. Křivánek, S. Popov, and P. Slusallek. Importance caching for complex illumination. Computer Graphics Forum (Proc. Eurographics), 31(2pt3):701–710, May 2012. [12] M. Hašan, E. VelázquezArmendáriz, F. Pellacini, and K. Bala. Tensor clustering for rendering manylight animations. 27(4):1105–1114, 2008. [13] M. Hašan, F. Pellacini, and K. Bala. Matrix rowcolumn sampling for the manylight problem. ACM Trans. Graph. (Proc. SIGGRAPH), 26(3):26–es, July 2007. [14] Y. Huo, R. Wang, S. Jin, X. Liu, and H. Bao. A matrix samplingandrecovery approach for manylights rendering. ACM Trans. Graph. (Proc. SIGGRAPH Asia), 34(6):1–12, 2015. [15] Y. Huo, R. Wang, R. Zheng, H. Xu, H. Bao, and S.E. Yoon. Adaptive incident radiance field sampling and reconstruction using deep reinforcement learning. ACM Trans. Graph. (Proc. SIGGRAPH), 39(1), Jan. 2020. [16] J. T. Kajiya. The rendering equation. In Proceedings of the 13th annual conference on Computer graphics and interactive techniques, pages 143–150, 1986. [17] A. Keller. Instant radiosity. In Proceedings of the 24th annual conference on Computer graphics and interactive techniques, pages 49–56, 1997. [18] A. J. Kok and F. W. Jansen. Source selection for the direct lighting computation in global illumination. In Photorealistic Rendering in Computer Graphics, pages 75–82. Springer, 1994. [19] T. Kollig and A. Keller. Illumination in the presence of weak singularities. In Monte Carlo and QuasiMonte Carlo Methods 2004, pages 245–257. Springer, 2006. [20] E. P. Lafortune and Y. D. Willems. A 5d tree to reduce the variance of monte carlo ray tracing. In Proceedings of the 6th Eurographics Workshop on Rendering, pages 11–20. Springer, 1995. [21] Y. Liu, K. Xu, and L.Q. Yan. Adaptive BRDForiented multiple importance sampling of many lights. 38(4):123–133, 2019. [22] P. Moreau, M. Pharr, and P. Clarberg. Dynamic manylight sampling for realtime ray tracing. In High Performance Graphics (Short Papers), pages 21–26, 2019. [23] T. Müller, M. Gross, and J. Novák. Practical path guiding for efficient lighttransport simulation. Computer Graphics Forum (Proc. EGSR), 36(4):91–100, June 2017. [24] T. Müller, B. McWilliams, F. Rousselle, M. Gross, and J. Novák. Neural importance sampling. ACM Trans. Graph., 38(5):145:1–145:19, Oct. 2019. [25] J. Ou and F. Pellacini. LightSlice: matrix slice sampling for the manylights problem. ACM Trans. Graph. (Proc. SIGGRAPH Asia), 30(6):179:1–179:8, 2011. [26] J. Pantaleoni. Importance sampling of many lights with reinforcement lightcuts learning. arXiv preprint arXiv:1911.10217, 2019. [27] J. Pantaleoni. Online path sampling control with progressive spatiotemporal filtering. SN Computer Science, 1(5):1–16, 2020. [28] E. Paquette, P. Poulin, and G. Drettakis. A light hierarchy for fast rendering of scenes with many lights. 17(3):63–74, 1998. [29] M. Pharr, W. Jakob, and G. Humphreys. Physically Based Rendering: From Theory to Implementation (3rd ed.). Morgan Kaufmann Publishers Inc., San Francisco, CA, USA, 3rd edition, Nov. 2016. [30] S. Popov, R. Ramamoorthi, F. Durand, and G. Drettakis. Probabilistic connections for bidirectional path tracing. Computer Graphics Forum (Proc. EGSR), 34(4):75–86, July 2015. [31] A. Rath, P. Grittmann, S. Herholz, P. Vévoda, P. Slusallek, and J. Křivánek. Varianceaware path guiding. ACM Trans. Graph. (Proc. SIGGRAPH), 39(4):151:1–151:12, July 2020. [32] T. Ritschel, T. Grosch, M. H. Kim, H.P. Seidel, C. Dachsbacher, and J. Kautz. Imperfect shadow maps for efficient computation of indirect illumination. ACM Trans. Graph. (Proc. SIGGRAPH Asia), 27(5):1–8, 2008. [33] H. Robbins and S. Monro. A stochastic approximation method. Ann. Math. Statist., 22(3):400–407, 1951. [34] B. Segovia, J. C. Iehl, R. Mitanchey, and B. Péroche. Bidirectional instant radiosity. In Proceedings of the 17th Eurographics Conference on Rendering Techniques, page 389–397. Eurographics Association, 2006. [35] P. Shirley, C. Wang, and K. Zimmerman. Monte carlo techniques for direct lighting calculations. ACM Trans. Graph., 15(1):1–36, Jan. 1996. [36] R. S. Sutton, A. G. Barto, et al. Introduction to reinforcement learning, volume 135. MIT press Cambridge, 1998. [37] E. Veach and L. J. Guibas. Optimally combining sampling techniques for monte carlo rendering. In Proceedings of the 22nd Annual Conference on Computer Graphics and Interactive Techniques, page 419–428. Association for Computing Machinery, 1995. [38] E. VelázquezArmendáriz, S. Zhao, M. Hašan, B. Walter, and K. Bala. Automatic bounding of programmable shaders for efficient global illumination. ACM Trans. Graph. (Proc. SIGGRAPH Asia), 28(5), 2009. [39] P. Vévoda, I. Kondapaneni, and J. Křivánek. Bayesian online regression for adaptive direct illumination sampling. ACM Trans. Graph. (Proc. SIGGRAPH), 37(4):125:1–125:12, 2018. [40] J. Vorba, O. Karlík, M. Sik, T. Ritschel, and J. Krivánek. Onlinelearning of parametric mixture models for light transport simulation. ACM Trans. Graph. (Proc. SIGGRAPH), 33(4):101:1–101:11, 2014. [41] B. Walter. Notes on the Ward BRDF. Program of Computer Graphics, Cornell University, Technical report PCG05, 6, 2005 [42] B. Walter, A. Arbree, K. Bala, and D. P. Greenberg. Multidimensional lightcuts. ACM Trans. Graph. (Proc. SIGGRAPH), 25(3):1081–1088, July 2006. [43] B. Walter, S. Fernandez, A. Arbree, K. Bala, M. Donikian, and D. P. Greenberg. Lightcuts: A scalable approach to illumination. ACM Trans. Graph. (Proc. SIGGRAPH), 24(3):1098–1107, 2005. [44] B. Walter, P. Khungurn, and K. Bala. Bidirectional lightcuts. ACM Trans. Graph. (Proc. SIGGRAPH), 31(4):1–11, 2012. [45] G. J. Ward. Adaptive shadow testing for ray tracing. In Photorealistic Rendering in Computer Graphics, pages 11–20. Springer, 1994. [46] C. J. Watkins and P. Dayan. Qlearning. Machine learning, 8(34): 279–292, 1992. [47] Y.T. Wu and Y.Y. Chuang. Visibilitycluster: Average directional visibility for manylight rendering. IEEE Trans. on Visualization and Computer Graphics, 19(9):1566–1578, 2013. [48] Y.T. Wu, T.M. Li, Y.H. Lin, and Y.Y. Chuang. Dual-matrix sampling for scalable translucent material rendering. IEEE Trans. on Visualization and Computer Graphics, 21(3):363–374, 2015. [49] C. Yuksel. Stochastic lightcuts. In HighPerformance Graphics, pages 27–32. The Eurographics Association, 2019. | |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/81287 | - |
| dc.description.abstract | "本篇論文提出了一個無偏差,在線的多光源渲染蒙地卡羅方法。我們的方法基於光源分層，我們採樣的概率基於我們的演算法已經得到的採樣結果。設計這樣的方法需要我們在嘈雜的採樣結果下做正確的分群決定，並能夠基於採樣結果得到好的採樣概率。我們的方法基於兩點精神。第一，我們從一個很小的光源分群出發找到一個較好的光源分群。這樣的方法能夠讓我們在很嘈雜的採樣結果下找到好的光源分群的方案。第二，我們採用隨機近似法讓我們從現有的採樣結果得到後驗概率來逼近目標分佈，證明出我們的方法一定能夠收斂。我們將我們的方法和現有的最先進的方法做對比，我們證明我們的方法在多光渲染的設定下能獲得更好的效果。" | zh_TW |
| dc.description.provenance | Made available in DSpace on 2022-11-24T03:40:55Z (GMT). No. of bitstreams: 1 U0001-2307202116054900.pdf: 7193828 bytes, checksum: 55453c197fb1257afadf6629c49c1f05 (MD5) Previous issue date: 2021 | en |
| dc.description.tableofcontents | Acknowledgements 3 摘要 5 Abstract 7 Contents 9 List of Figures 11 List of Tables 15 Chapter 1 Introduction 1 Chapter 2 Related Work 5 2.1 Rendering with many lights. . . . . . . . . . . . . . . . . . . . . . . 5 2.2 Path guiding. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 6 2.3 Reinforcement learning in rendering. . . . . . . . . . . . . . . . . . 6 Chapter 3 Background: Rendering with Direct Illumination 9 Chapter 4 Background: Rendering with Direct Illumination 13 Chapter 5 Method 17 5.1 Initialization . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 17 5.2 Learning to Sample and Cluster . . . . . . . . . . . . . . . . . . . . 18 5.2.1 Relation to Reinforcement Learning . . . . . . . . . . . . . . . . . 21 Chapter 6 Results 23 6.1 Experiments Set Up . . . . . . . . . . . . . . . . . . . . . . . . . . 23 6.2 Comparisons . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 24 6.2.1 Ablation Study . . . . . . . . . . . . . . . . . . . . . . . . . . . . 29 Chapter 7 Limitation and Future work 31 Chapter 8 Conclusion 33 References 35 Appendix A — Equal-time Comparison 41 A.1 Results . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 41 Appendix B — Details 43 B.1 Stochastic lightcuts . . . . . . . . . . . . . . . . . . . . . . . . . . . 43 B.2 Initialization after splitting a cluster . . . . . . . . . . . . . . . . . . 44 B.3 Proof of Convergence of Our method . . . . . . . . . . . . . . . . . 45 | |
| dc.language.iso | en | |
| dc.subject | 多光渲染 | zh_TW |
| dc.subject | 直接照明 | zh_TW |
| dc.subject | 光線追蹤 | zh_TW |
| dc.subject | 強化學習 | zh_TW |
| dc.subject | Direct Illumination | en |
| dc.subject | ManyLight Rendering | en |
| dc.subject | Ray Tracing | en |
| dc.subject | ReinforcementLearning | en |
| dc.title | 多光渲染之光源分群的機器學習方法 | zh_TW |
| dc.title | Learning to cluster in rendering with many lights | en |
| dc.date.schoolyear | 109-2 | |
| dc.description.degree | 碩士 | |
| dc.contributor.oralexamcommittee | 賴祐吉(Hsin-Tsai Liu),蔡侑庭(Chih-Yang Tseng),李子懋 | |
| dc.subject.keyword | 直接照明,光線追蹤,多光渲染,強化學習, | zh_TW |
| dc.subject.keyword | Direct Illumination,Ray Tracing,ManyLight Rendering,ReinforcementLearning, | en |
| dc.relation.page | 45 | |
| dc.identifier.doi | 10.6342/NTU202101690 | |
| dc.rights.note | 同意授權(限校園內公開) | |
| dc.date.accepted | 2021-07-27 | |
| dc.contributor.author-college | 電機資訊學院 | zh_TW |
| dc.contributor.author-dept | 資訊工程學研究所 | zh_TW |
| 顯示於系所單位： | 資訊工程學系 | |
文件中的檔案：
| 檔案 | 大小 | 格式 | |
|---|---|---|---|
| U0001-2307202116054900.pdf 授權僅限NTU校內IP使用（校園外請利用VPN校外連線服務） | 7.03 MB | Adobe PDF |
系統中的文件，除了特別指名其著作權條款之外，均受到著作權保護，並且保留所有的權利。