{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,21]],"date-time":"2026-03-21T02:16:03Z","timestamp":1774059363766,"version":"3.50.1"},"reference-count":51,"publisher":"Association for Computing Machinery (ACM)","issue":"4","license":[{"start":{"date-parts":[[2020,8,12]],"date-time":"2020-08-12T00:00:00Z","timestamp":1597190400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Graph."],"published-print":{"date-parts":[[2020,8,31]]},"abstract":"<jats:p>Path guiding is a promising tool to improve the performance of path tracing algorithms. However, not much research has investigated what target densities a guiding method should strive to learn for optimal performance. Instead, most previous work pursues the zero-variance goal: The local decisions are guided under the assumption that all other decisions along the random walk will be sampled perfectly. In practice, however, many decisions are poorly guided, or not guided at all. Furthermore, learned distributions are often marginalized, e.g., by neglecting the BSDF. We present a generic procedure to derive theoretically optimal target densities for local path guiding. These densities account for variance in nested estimators, and marginalize provably well over, e.g., the BSDF. We apply our theory in two state-of-the-art rendering applications: a path guiding solution for unidirectional path tracing [M\u00fcller et al. 2017] and a guiding method for light source selection for the many lights problem [V\u00e9voda et al. 2018]. In both cases, we observe significant improvements, especially on glossy surfaces. The implementations for both applications consist of trivial modifications to the original code base, without introducing any additional overhead.<\/jats:p>","DOI":"10.1145\/3386569.3392441","type":"journal-article","created":{"date-parts":[[2020,8,12]],"date-time":"2020-08-12T11:44:27Z","timestamp":1597232667000},"update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":33,"title":["Variance-aware path guiding"],"prefix":"10.1145","volume":"39","author":[{"given":"Alexander","family":"Rath","sequence":"first","affiliation":[{"name":"DFKI and Saarland University, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pascal","family":"Grittmann","sequence":"additional","affiliation":[{"name":"Saarland University, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sebastian","family":"Herholz","sequence":"additional","affiliation":[{"name":"University of T\u00fcbingen, Germany and Intel Corporation"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Petr","family":"V\u00e9voda","sequence":"additional","affiliation":[{"name":"Charles University, Prague and Chaos Czech a.s., Czech Republic"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Philipp","family":"Slusallek","sequence":"additional","affiliation":[{"name":"Saarland University, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jaroslav","family":"K\u0159iv\u00e1nek","sequence":"additional","affiliation":[{"name":"Charles University, Prague and Chaos Czech a.s., Czech Republic"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2020,8,12]]},"reference":[{"key":"e_1_2_2_1_1","volume-title":"Offline Deep Importance Sampling for Monte Carlo Path Tracing. Comput. Graph. Forum (Proceedings of Pacific Graphics 2019) 38, 7","author":"Bako Steve","year":"2019","unstructured":"Steve Bako, Mark Meyer, Tony DeRose, and Pradeep Sen. 2019. Offline Deep Importance Sampling for Monte Carlo Path Tracing. Comput. Graph. Forum (Proceedings of Pacific Graphics 2019) 38, 7 (2019), 527--542."},{"key":"e_1_2_2_2_1","volume-title":"Comput. Graph. Forum","author":"Bashford-Rogers Thomas","year":"1837","unstructured":"Thomas Bashford-Rogers, Kurt Debattista, and Alan Chalmers. 2012. A significance cache for accelerating global illumination. In Comput. Graph. Forum, Vol. 31. Wiley Online Library, 1837--1851."},{"key":"e_1_2_2_3_1","unstructured":"Benedikt Bitterli. 2016. Rendering resources. https:\/\/benedikt-bitterli.me\/resources\/"},{"key":"e_1_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3182159"},{"key":"e_1_2_2_5_1","article-title":"Double Hierarchies for Directional Importance Sampling in Monte Carlo Rendering","volume":"6","author":"Bus Norbert","year":"2017","unstructured":"Norbert Bus and Tamy Boubekeur. 2017. Double Hierarchies for Directional Importance Sampling in Monte Carlo Rendering. Journal of Computer Graphics Techniques (JCGT) 6, 3 (28 August 2017), 25--37. http:\/\/jcgt.org\/published\/0006\/03\/02","journal-title":"Journal of Computer Graphics Techniques (JCGT)"},{"key":"e_1_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3182161"},{"key":"e_1_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3182160"},{"key":"e_1_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/2366145.2366211"},{"key":"e_1_2_2_9_1","volume-title":"Comput. Graph. Forum","author":"Georgiev Iliyan","unstructured":"Iliyan Georgiev, Jaroslav K\u0159iv\u00e1nek, Stefan Popov, and Philipp Slusallek. 2012b. Importance caching for complex illumination. In Comput. Graph. Forum, Vol. 31. Wiley Online Library, 701--710."},{"key":"e_1_2_2_10_1","volume-title":"Comput. Graph. Forum (EGSR '18)","author":"Grittmann Pascal","unstructured":"Pascal Grittmann, Ars\u00e8ne P\u00e9rard-Gayot, Philipp Slusallek, and Jaroslav K\u0159iv\u00e1nek. 2018. Efficient Caustic Rendering with Lightweight Photon Mapping. In Comput. Graph. Forum (EGSR '18), Vol. 37. Wiley Online Library, 133--142."},{"key":"e_1_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/2963097"},{"key":"e_1_2_2_12_1","volume-title":"Eurographics Symposium on Rendering","volume":"2018","author":"Guo Jerry","year":"2018","unstructured":"Jerry Guo, Pablo Bauszat, Jacco Bikker, and Elmar Eisemann. 2018. Primary sample space path guiding. In Eurographics Symposium on Rendering, Vol. 2018. The Eurographics Association, 73--82."},{"key":"e_1_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/2019627.2019633"},{"key":"e_1_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/1409060.1409083"},{"key":"e_1_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/2366145.2366210"},{"key":"e_1_2_2_16_1","volume-title":"Optimal Combination of Techniques in Multiple Importance Sampling","author":"Havran Vlastimil","unstructured":"Vlastimil Havran and Mateu Sbert. 2014. Optimal Combination of Techniques in Multiple Importance Sampling. ACM, New York, NY, 141--150."},{"key":"e_1_2_2_17_1","volume-title":"EGSR '18 EI&I (EGSR '18)","author":"Herholz Sebastian","year":"2018","unstructured":"Sebastian Herholz, Oskar Elek, Jens Schindel, Jaroslav K\u0159iv\u00e1nek, and Hendrik Lensch. 2018. A Unified Manifold Framework for Efficient BRDF Sampling based on Parametric Mixture Model. In EGSR '18 EI&I (EGSR '18). Eurographics Association."},{"key":"e_1_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.5555\/3071773.3071781"},{"key":"e_1_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3230635"},{"key":"e_1_2_2_20_1","volume-title":"Importance Sampling with Hemispherical Particle Footprints (SCCG '02)","author":"Hey Heinrich","year":"2002","unstructured":"Heinrich Hey and Werner Purgathofer. 2002. Importance Sampling with Hemispherical Particle Footprints (SCCG '02). ACM, 107--114."},{"key":"e_1_2_2_21_1","unstructured":"Wenzel Jakob. 2010. Mitsuba renderer. http:\/\/www.mitsuba-renderer.org."},{"key":"e_1_2_2_22_1","doi-asserted-by":"crossref","unstructured":"Henrik Wann Jensen. 1995. Importance Driven Path Tracing using the Photon Map. In Rendering Techniques.","DOI":"10.1007\/978-3-7091-9430-0_31"},{"key":"e_1_2_2_23_1","volume-title":"Rendering Techniques' 96","author":"Jensen Henrik Wann","unstructured":"Henrik Wann Jensen. 1996. Global illumination using photon maps. In Rendering Techniques' 96. Springer, 21--30."},{"key":"e_1_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/15886.15902"},{"key":"e_1_2_2_25_1","volume-title":"Comput. Graph. Forum","author":"Kaplanyan Anton S","unstructured":"Anton S Kaplanyan and Carsten Dachsbacher. 2013. Path space regularization for holistic and robust light transport. In Comput. Graph. Forum, Vol. 32. Wiley Online Library, 63--72."},{"key":"e_1_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3355089.3356565"},{"key":"e_1_2_2_27_1","doi-asserted-by":"crossref","unstructured":"Alexander Keller Luca Fascione Marcos Fajardo Iliyan Georgiev Per H Christensen Johannes Hanika Christian Eisenacher and Gregory Nichols. 2015. The path tracing revolution in the movie industry.. In SIGGRAPH Courses. 24--1.","DOI":"10.1145\/2776880.2792699"},{"key":"e_1_2_2_28_1","volume-title":"Optimal Multiple Importance Sampling. ACM Trans. Graph. (SIGGRAPH 2019) 38, 4 (July","author":"Kondapaneni Ivo","year":"2019","unstructured":"Ivo Kondapaneni, Petr V\u00e9voda, Pascal Grittmann, Tom\u00e1\u0161 Sk\u0159ivan, Philipp Slusallek, and Jaroslav K\u0159iv\u00e1nek. 2019. Optimal Multiple Importance Sampling. ACM Trans. Graph. (SIGGRAPH 2019) 38, 4 (July 2019), 37:1--37:14."},{"key":"e_1_2_2_29_1","volume-title":"Willems","author":"Lafortune Eric P.","year":"1993","unstructured":"Eric P. Lafortune and Yves D. Willems. 1993. Bi-Directional Path Tracing. 93 (Dec. 1993), 145--153."},{"key":"e_1_2_2_30_1","volume-title":"Willems","author":"Lafortune Eric P.","year":"1995","unstructured":"Eric P. Lafortune and Yves D. Willems. 1995. A 5D Tree to Reduce the Variance of Monte Carlo Ray Tracing. In Rendering Techniques."},{"key":"e_1_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.13227"},{"key":"e_1_2_2_32_1","volume-title":"Neural importance sampling. arXiv preprint arXiv:1808.03856","author":"M\u00fcller Thomas","year":"2018","unstructured":"Thomas M\u00fcller, Brian McWilliams, Fabrice Rousselle, Markus Gross, and Jan Nov\u00e1k. 2018. Neural importance sampling. arXiv preprint arXiv:1808.03856 (2018)."},{"key":"e_1_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.2000.10473909"},{"key":"e_1_2_2_34_1","volume-title":"Importance Sampling of Many Lights with Reinforcement Lightcuts Learning. arXiv preprint arXiv:1911.10217","author":"Pantaleoni Jacopo","year":"2019","unstructured":"Jacopo Pantaleoni. 2019. Importance Sampling of Many Lights with Reinforcement Lightcuts Learning. arXiv preprint arXiv:1911.10217 (2019)."},{"key":"e_1_2_2_35_1","volume-title":"Notes on optimal approximations for importance sampling. arXiv preprint arXiv:1707.08358","author":"Pantaleoni Jacopo","year":"2017","unstructured":"Jacopo Pantaleoni and Eric Heitz. 2017. Notes on optimal approximations for importance sampling. arXiv preprint arXiv:1707.08358 (2017)."},{"key":"e_1_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/RT.2008.4634630"},{"key":"e_1_2_2_37_1","unstructured":"Matt Pharr Wenzel Jakob and Greg Humphreys. 2016. Physically based rendering: From theory to implementation. Morgan Kaufmann."},{"key":"e_1_2_2_38_1","doi-asserted-by":"crossref","unstructured":"Florian Reibold Johannes Hanika Alisa Jung and Carsten Dachsbacher. 2018. Selective guided sampling with complete light transport paths. In SIGGRAPH Asia 2018 Technical Papers. ACM 223.","DOI":"10.1145\/3272127.3275030"},{"key":"e_1_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.5555\/3151666.3151712"},{"key":"e_1_2_2_40_1","volume-title":"Survey of Markov Chain Monte Carlo Methods in Light Transport Simulation","author":"\u0160ik Martin","year":"2018","unstructured":"Martin \u0160ik and Jaroslav K\u0159iv\u00e1nek. 2018. Survey of Markov Chain Monte Carlo Methods in Light Transport Simulation. IEEE Transactions on Visualization and Computer Graphics (2018), 1--1."},{"key":"e_1_2_2_41_1","unstructured":"Martin \u0160ik and Jaroslav K\u0159iv\u00e1nek. 2019. Implementing One-Click Caustics in Corona Renderer. (2019)."},{"key":"e_1_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/2980179.2982411"},{"key":"e_1_2_2_43_1","volume-title":"Robust Monte Carlo methods for light transport simulation","author":"Veach Eric","unstructured":"Eric Veach. 1997. Robust Monte Carlo methods for light transport simulation. Stanford University PhD thesis."},{"key":"e_1_2_2_44_1","volume-title":"Photorealistic Rendering Techniques","author":"Veach Eric","unstructured":"Eric Veach and Leonidas Guibas. 1995a. Bidirectional estimators for light transport. In Photorealistic Rendering Techniques. Springer, 145--167."},{"key":"e_1_2_2_45_1","volume-title":"Optimally Combining Sampling Techniques for Monte Carlo Rendering. In SIGGRAPH '95","author":"Veach Eric","year":"1995","unstructured":"Eric Veach and Leonidas J Guibas. 1995b. Optimally Combining Sampling Techniques for Monte Carlo Rendering. In SIGGRAPH '95. ACM, 419--428."},{"key":"e_1_2_2_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/258734.258775"},{"key":"e_1_2_2_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201340"},{"key":"e_1_2_2_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/3305366.3328091"},{"key":"e_1_2_2_49_1","volume-title":"On-line Learning of Parametric Mixture Models for Light Transport Simulation. ACM Trans. Graph. (Proceedings of SIGGRAPH 2014)","author":"Vorba Ji\u0159\u00ed","year":"2014","unstructured":"Ji\u0159\u00ed Vorba, Ond\u0159ej Karl\u00edk, Martin \u0160ik, Tobias Ritschel, and Jaroslav K\u0159iv\u00e1nek. 2014. On-line Learning of Parametric Mixture Models for Light Transport Simulation. ACM Trans. Graph. (Proceedings of SIGGRAPH 2014) 33, 4 (2014)."},{"key":"e_1_2_2_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/2897824.2925912"},{"key":"e_1_2_2_51_1","volume-title":"Comput. Graph. Forum","author":"Zheng Quan","unstructured":"Quan Zheng and Matthias Zwicker. 2019. Learning to importance sample in primary sample space. In Comput. Graph. Forum, Vol. 38. Wiley Online Library, 169--179."}],"container-title":["ACM Transactions on Graphics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3386569.3392441","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3386569.3392441","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,25]],"date-time":"2025-06-25T05:41:13Z","timestamp":1750830073000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3386569.3392441"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,8,12]]},"references-count":51,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2020,8,31]]}},"alternative-id":["10.1145\/3386569.3392441"],"URL":"https:\/\/doi.org\/10.1145\/3386569.3392441","relation":{},"ISSN":["0730-0301","1557-7368"],"issn-type":[{"value":"0730-0301","type":"print"},{"value":"1557-7368","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,8,12]]},"assertion":[{"value":"2020-08-12","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}